Asset Registry

Machine-readable-style registry for repository assets. Generated from frontmatter and file-system discovery.

Agents

Agent	File	Category	Visibility	Model	Allowed Skills	Description
agent-designer	agents/basecoat-10-core-agent-designer.agent.md	agent-development	basic	gpt-5.3-codex	—	Agent factory specialist. USE FOR: creating agent specs, auditing agent/skill definitions, capability-based routing decisions, and revising weak specs. DO NOT USE FOR: product feature coding, infrastructure deployment, unrelated code review.
agentic-sdlc-autonomy	agents/agentic-sdlc-autonomy.agent.md	Uncategorized	specialized	not-specified	—	Audit, measure, implement, and operate rules-based human-in-the-loop autonomy for agent-operated repositories. Use when evaluating or improving agentic SDLC governance: PR risk classification (A0-A5 levels), auto-merge policy, merge queue gates, deployment lane policy, DB migration controls, IaC safety rules, runner isolation, production approval flows, and policy-versus-settings drift.
agentops	agents/basecoat-10-core-agentops.agent.md	Uncategorized	internal	claude-sonnet-4.6	—	Agent operations and infrastructure specialist. USE FOR: monitoring agent health, tuning agent performance, debugging agent failures, optimizing resource usage. DO NOT USE FOR: individual agent tasks, direct coding.
api-designer	agents/basecoat-10-core-api-designer.agent.md	Uncategorized	basic	gpt-5.3-codex	—	REST API and contract design specialist. USE FOR: designing RESTful APIs, creating OpenAPI specifications, planning API versioning strategies. DO NOT USE FOR: API implementation, testing.
api-security	agents/basecoat-50-security-api-security.agent.md	Uncategorized	specialized	claude-sonnet-4.6	—	API Security Agent for comprehensive API threat modeling, OWASP API Security Top 10 assessment, and secure API design. Covers authentication, authorization, rate limiting, and API-specific vulnerabilities. USE FOR: run OWASP API Top 10 assessment, model API threats with STRIDE, audit auth flows. DO NOT USE FOR: container image scanning, general code review.
app-inventory	agents/basecoat-10-core-app-inventory.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Scans legacy applications to discover dependencies, identify technology stacks, assess migration complexity, and generate architecture diagrams for portfolio analysis. USE FOR: scan legacy app tech stack, assess migration complexity, generate dependency inventory. DO NOT USE FOR: writing new code, live production monitoring.
azure-landing-zone	agents/basecoat-40-azure-azure-landing-zone.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Azure Landing Zone (ESLZ) agent for scaffolding enterprise-scale landing zones following Microsoft's Cloud Adoption Framework. Use when designing management group hierarchies, platform subscriptions, hub networking, policy baselines, or landing zone vending templates.
backend-dev	agents/basecoat-10-core-backend-dev.agent.md	Uncategorized	basic	gpt-5.3-codex	—	Backend and services development specialist. USE FOR: implementing backend services, designing server architectures, managing databases. DO NOT USE FOR: frontend work, DevOps operations.
bom-validator	agents/basecoat-10-core-bom-validator.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when validating a Workcell BOM against the plant registry before S2 starts. USE FOR: schema validation, CAF naming checks, circular dependency detection, and GitHub check results. DO NOT USE FOR: runtime state merges or cutover decisions.
branch-hygiene-sweeper	agents/basecoat-10-core-branch-hygiene-sweeper.agent.md	Uncategorized	specialized	gpt-5.4-mini	—	Use when cleaning stale branches, dangling refs, and release branch hygiene while preserving active work. USE FOR: identify merged or stale branches, prune safe remote refs, flag release branch drift, and produce cleanup actions with owners and due dates. DO NOT USE FOR: deleting branches with open PRs, changing branch protection, or resolving merge conflicts.
broken-build-troubleshooter	agents/basecoat-60-workflow-broken-build-troubleshooter.agent.md	Uncategorized	basic	gpt-5.4-mini	—	Use when CI or local builds are failing and the team needs fast, repeatable triage to isolate root cause and restore green status. USE FOR: classify failure signatures, pinpoint failing stage/test/toolchain segment, propose minimal safe remediation, and generate a fix validation checklist. DO NOT USE FOR: feature implementation, long-form architecture documents, or security incident response ownership.
build-master	agents/basecoat-60-workflow-build-master.agent.md	Workflow	specialized	claude-sonnet-4.5	build-master-control-plane, build-failure-triage, escalation-routing, dependency-blocker-monitoring	Background merge-control agent that keeps healthy lanes moving while isolating broken lanes and dispatching cloud break-fix PRs. USE FOR: lane-aware merge orchestration, CI break containment, cloud fix delegation, and safe resume after recovery. DO NOT USE FOR: bypassing branch protection, direct pushes to protected branches, or autonomous high-risk security/infra remediations.
change-isolation-architect	agents/basecoat-10-core-change-isolation-architect.agent.md	Uncategorized	basic	gpt-5.3-codex	—	Designs layered CI/CD isolation so independent domains (for example mobile, database, portal, extension, and infra) can evolve and release separately without cross-triggered pipeline noise.
chaos-engineer	agents/basecoat-10-core-chaos-engineer.agent.md	Uncategorized	basic	gpt-5.3-codex	—	Chaos engineering agent for fault injection, game days, resilience scoring, recovery validation, and SLO-aware resilience experiments. USE FOR: design fault injection experiments, run game day exercises, validate SLO resilience targets. DO NOT USE FOR: debugging application bugs, writing unit tests.
ci-audit	agents/basecoat-50-security-ci-audit.agent.md	Uncategorized	specialized	gpt-5.4-mini	—	Use when asked to audit repository governance posture or produce a governance evidence pack. USE FOR: auditing branch protection, required status checks, merge queue configuration, environment protection rules, production reviewers, runner groups, workflow dispatch access, CODEOWNERS enforcement, and policy-versus-settings gaps for a single repository. DO NOT USE FOR: writing application code, general code reviews, org-level enterprise policy administration, or infrastructure-as-code development.
ci-failure-escalation	agents/basecoat-60-workflow-ci-failure-escalation.agent.md	Uncategorized	basic	gpt-5.4-mini	—	Detects N consecutive CI failures on the same workflow job, opens a blocking issue, and gates further deploys to that environment — the andon cord / halt-the-line pattern for CI/CD pipelines. USE FOR: gate deploys on CI failures, open blocking issues, enforce halt-line policy. DO NOT USE FOR: fixing failing tests, writing CI config.
code-review	agents/basecoat-90-quality-code-review.agent.md	Uncategorized	basic	claude-haiku-4.5	—	Code review and quality gate specialist. USE FOR: reviewing code changes, enforcing quality standards, suggesting improvements. DO NOT USE FOR: writing code, direct fixes.
config-auditor	agents/basecoat-50-security-config-auditor.agent.md	Uncategorized	specialized	gpt-5.4-mini	—	Configuration auditor for detecting committed secrets and sensitive config. USE FOR: scanning repositories for hardcoded credentials, API keys, and PII; enforcing encryption standards for secrets at rest; generating compliance reports; performing pre-commit validation. DO NOT USE FOR: real-time monitoring, incident response (use Secrets Manager instead), general code reviews.
Container Security	agents/basecoat-50-security-container-security.agent.md	Uncategorized	specialized	claude-sonnet-4.6	—	Container and Kubernetes security — Pod Security Standards, runtime security, CSPM findings, image scanning, and supply chain security for containerized workloads. USE FOR: scan container images for CVEs, audit Pod Security Standards, assess Kubernetes runtime security. DO NOT USE FOR: writing application code, network firewall rules.
containerization-planner	agents/basecoat-30-ai-containerization-planner.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Helps assess containerization readiness, choose deployment platforms (Docker/AKS/ACA), and generate container configurations including Dockerfiles, multi-stage builds, health probes, resource limits, and deployment manifests. USE FOR: containerize an app, choose AKS vs ACA, generate Dockerfiles. DO NOT USE FOR: image scanning, cluster incidents.
contract-testing	agents/basecoat-10-core-contract-testing.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Contract Testing Agent for consumer-driven contracts, E2E testing strategy, and mutation testing for distributed systems. USE FOR: write Pact consumer-driven contracts, design service integration tests, set up contract verification in CI. DO NOT USE FOR: load testing, manual QA workflows.
daily-standup-facilitator	agents/basecoat-30-ai-daily-standup-facilitator.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when running daily standup ceremonies to surface blockers, dependencies, and near-term execution risk. USE FOR: extract actionable updates, identify blockers needing escalation, map dependencies across team members, and produce a day plan with owners. DO NOT USE FOR: writing feature code, replacing sprint planning, or long-term roadmap analysis.
Data Integrity	agents/basecoat-80-data-data-integrity.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	>
data-architect	agents/basecoat-80-data-data-architect.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Data architecture design specialist. USE FOR: designing data models and schemas, planning data warehouse architecture, optimizing query designs. DO NOT USE FOR: ETL operations, data pipeline troubleshooting.
data-pipeline	agents/basecoat-60-workflow-data-pipeline.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Data pipeline agent for medallion lakehouse architecture, data quality, ML pipeline orchestration, and feature store integration. Use when building or reviewing bronze/silver/gold Delta Lake pipelines, data quality checks, feature engineering, or ML training workflows.
data-tier	agents/basecoat-80-data-data-tier.agent.md	Uncategorized	basic	gpt-5.3-codex	—	Data persistence and storage optimization. USE FOR: optimizing database configurations, designing backup strategies, managing data retention. DO NOT USE FOR: application development, real-time operations.
database-migration	agents/basecoat-80-data-database-migration.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.
dataops	agents/basecoat-80-data-dataops.agent.md	Uncategorized	basic	gpt-5.3-codex	—	Data operations and pipeline management. USE FOR: managing data pipelines, monitoring data quality, optimizing data flow. DO NOT USE FOR: data analysis, business intelligence.
definition-of-done	agents/basecoat-10-core-definition-of-done.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Validate that a feature, PR, or release meets the Definition of Done before closing. Enforces testing evidence, config verification, response validation, and acceptance criteria. USE FOR: check PR meets DoD, validate acceptance criteria, verify release readiness. DO NOT USE FOR: writing acceptance criteria, implementing features.
dependency-blocker-monitor	agents/basecoat-10-core-dependency-blocker-monitor.agent.md	Uncategorized	basic	gpt-5.4-mini	—	Use when monitoring workcell BOM dependencies and cell health to open or resolve blocker issues when a cell fails or recovers. USE FOR: read workcell BOM dependencies, monitor cell deployment status, create blocker issues, and resolve them on recovery. DO NOT USE FOR: general incident response, application code, or one-off issue triage.
dependency-lifecycle	agents/basecoat-10-core-dependency-lifecycle.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Agent for managing dependency updates, tracking breaking changes, planning upgrade paths, monitoring vulnerabilities, analyzing semantic versioning, and generating migration guides. USE FOR: plan upgrade paths, generate migration guides, audit dependency CVEs. DO NOT USE FOR: writing new features, infrastructure provisioning.
dependency-update-advisor	agents/basecoat-10-core-dependency-update-advisor.agent.md	Uncategorized	basic	gpt-5.4-mini	—	Reviews Dependabot pull requests and posts a structured risk assessment comment: semver bump type, breaking change likelihood, suggested test focus areas, and known CVE context. USE FOR: assess Dependabot PR risk, evaluate semver bump safety, get CVE context for dependency update. DO NOT USE FOR: creating Dependabot config, general code review.
devops-engineer	agents/basecoat-10-core-devops-engineer.agent.md	Uncategorized	basic	gpt-5.3-codex	—	DevOps and infrastructure automation specialist. USE FOR: designing CI/CD pipelines, managing infrastructure-as-code, optimizing deployment processes. DO NOT USE FOR: application code, product feature development.
domain-designer	agents/basecoat-30-ai-domain-designer.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Domain-driven design specialist. USE FOR: designing domain models, planning domain-oriented architectures, designing bounded contexts. DO NOT USE FOR: implementation, code generation.
dotnet-modernization-advisor	agents/basecoat-20-lang-dotnet-modernization-advisor.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Advisor for .NET modernization assessment, upgrade planning, and execution guidance. Use when migrating legacy .NET Framework/older .NET solutions to modern .NET versions.
e2e-test-strategy	agents/basecoat-90-quality-e2e-test-strategy.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	E2E Test Strategy Agent for end-to-end testing orchestration, critical path identification, flakiness prevention, and cross-browser coverage. Covers Playwright, Cypress, Selenium patterns and integration with CI/CD pipelines. USE FOR: design E2E suite, map critical user paths, fix flaky tests. DO NOT USE FOR: unit testing, contract testing.
escalation-router	agents/basecoat-10-core-escalation-router.agent.md	Uncategorized	advanced	gpt-5.4-mini	—	Use when high-risk decisions need a human approver and a PR-comment approval trail. USE FOR: release signoff, irreversible changes, compliance gates. DO NOT USE FOR: routine automation.
exploratory-charter	agents/basecoat-10-core-exploratory-charter.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when you need time-boxed exploratory testing sessions. Generates mission-driven charters with scope, triage routing, and evidence capture. Automatically files GitHub Issues for automation candidates found during exploration.
factory-conductor	agents/basecoat-10-core-factory-conductor.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when reading .factory-state.json and auto-queuing the next ready wave of factory work. USE FOR: route S2/S3/S4 work, batch dispatch by wave, and ping the right follow-up workflow. DO NOT USE FOR: state normalization, BOM validation, or product backlog prioritization.
factory-state-curator	agents/basecoat-10-core-factory-state-curator.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when merging Workcell intake YAML, GitHub labels, and gate results into a single S1-S5 state snapshot. USE FOR: normalize station state, publish .factory-state.json, reconcile blockers, and surface stale work. DO NOT USE FOR: implementing product code or changing workflow policy.
failure-pattern-process	agents/basecoat-30-ai-failure-pattern-process.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Failure pattern process agent for evidence-first mining, raw logging, triage, and enhancement planning. USE FOR: mining failure signals across issues/PRs/CI/logs/incidents, producing append-only raw findings logs, classifying common versus repo-specific patterns with rationale, and building prioritized enhancement plans with early-detection gates. DO NOT USE FOR: implementing feature code changes, auto-remediating production incidents, or bypassing evidence and gate requirements.
feedback-loop	agents/basecoat-10-core-feedback-loop.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Continuous learning and optimization through user feedback collection, prompt effectiveness tracking, outcome measurement, A/B testing, regression detection, and instruction refinement. USE FOR: track prompt effectiveness, run A/B test on instructions, detect quality regression. DO NOT USE FOR: product feature feedback, writing new prompts.
finops-advisor	agents/basecoat-10-core-finops-advisor.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	FinOps advisor for cloud cost governance, cost optimization, chargeback/showback models, and 12-Factor App best practices for cost efficiency. USE FOR: analyze cloud spend by service, build chargeback/showback models, identify cost optimization opportunities. DO NOT USE FOR: live incident response, infrastructure provisioning.
flow-admission-controller	agents/flow-admission-controller.agent.md	flow-governance	advanced	claude-sonnet-4.6	—	Use when designing or tuning intake controls for PR volume, merge-queue admission, and reviewer/runner capacity limits. USE FOR: WIP limit policies, queue admission rules, stale PR handling, and safe load-shedding design. DO NOT USE FOR: overriding branch protections manually, skipping approvals, or implementing unrelated product features.
flow-auditor	agents/flow-auditor.agent.md	flow-governance	specialized	gpt-5.4-mini	—	Use when auditing PR intake, merge queue health, CI tier efficiency, and stale-branch pressure across repositories. USE FOR: queue bottleneck audits, CI waste analysis, PR aging reviews, merge-path risk scoring, and evidence-backed findings. DO NOT USE FOR: writing feature code, merging PRs without approval, or changing branch protections directly.
flow-governance-conductor	agents/flow-governance-conductor.agent.md	flow-governance	advanced	gpt-5.3-codex	—	Use when coordinating flow-governance analysis across code, PRs, issues, skills, and scripts. USE FOR: reusing existing flow/CI/governance skills first, mapping findings to current agents and scripts, identifying missing skill/script coverage, and producing issue-ready gap backlogs. DO NOT USE FOR: writing product features, bypassing branch or environment protections, or force-merging pull requests.
flow-optimizer	agents/flow-optimizer.agent.md	flow-governance	advanced	claude-sonnet-4.6	—	Use when building an optimization program that combines audit evidence with prioritized fixes and execution sequencing. USE FOR: phased flow optimization plans, merge-queue and CI policy tuning, target KPI definition, and rollout risk reduction. DO NOT USE FOR: one-off bugfix coding, ad hoc release approvals, or force-merging around failed checks.
flow-suggester	agents/flow-suggester.agent.md	flow-governance	specialized	gpt-5.4-mini	—	Use when converting audit findings into prioritized, issue-ready fixes with acceptance criteria and owners. USE FOR: translating audit evidence into GitHub issues, prioritizing queue and CI fixes, auto-creating high-confidence issues, sequencing remediation work, and defining measurable outcomes. DO NOT USE FOR: running uncontrolled migrations, bypassing governance gates, or shipping code changes directly.
flow-tracker	agents/flow-tracker.agent.md	flow-governance	specialized	gpt-5.4-mini	—	Use when tracking repository flow metrics over time and recommending corrective actions when trends degrade. USE FOR: weekly flow scorecards, trend analysis, regression alerts, and metric-backed improvement suggestions. DO NOT USE FOR: speculative architecture redesign, editing production code, or replacing incident response workflows.
frontend-dev	agents/basecoat-10-core-frontend-dev.agent.md	Uncategorized	basic	gpt-5.3-codex	—	Frontend and UI development specialist. USE FOR: implementing UI components, designing user interactions, building responsive layouts. DO NOT USE FOR: backend development, infrastructure.
github-security-posture	agents/basecoat-50-security-github-security-posture.agent.md	Uncategorized	specialized	claude-sonnet-4.5	security	GitHub organization security posture auditor. USE FOR: auditing GitHub organization settings and policies, reviewing branch protection configurations, analyzing secret scanning and Dependabot alerts, assessing team and RBAC permissions, evaluating OAuth app restrictions. DO NOT USE FOR: fixing security issues (use individual remediation agents), real-time threat detection, application code security review.
gitops-engineer	agents/basecoat-10-core-gitops-engineer.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	GitOps and deployment automation specialist. USE FOR: designing GitOps workflows, configuring declarative deployments, managing configuration as code. DO NOT USE FOR: manual deployments, emergency operations.
governance-auditor	agents/governance-auditor.agent.md	governance	specialized	gpt-5.4-mini	—	Use when auditing issue and PR metadata, label drift, template gaps, and workflow enforcement coverage. USE FOR: label audits, template consistency checks, workflow drift reviews, gap identification, and issue-ready findings. DO NOT USE FOR: writing application code, implementing product features, or changing labels without evidence.
governance-author	agents/governance-author.agent.md	governance	specialized	claude-sonnet-4.6	—	Use when writing or revising common-vs-specific governance guidance, canonical label contracts, and migration notes. USE FOR: drafting docs/reference/governance-contract.md, separating shared rules from repo-specific rules, mapping legacy labels to canonical labels, and planning governance issue backlogs. DO NOT USE FOR: implementation code, release management, or ad hoc issue cleanup.
guardrail	agents/basecoat-30-ai-guardrail.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Guardrail validation agent for checking outputs against safety, quality, compliance, and formatting rules before delivery. USE FOR: validate agent output against safety rules, enforce quality gates on generated content, check compliance formatting before delivery. DO NOT USE FOR: writing new code or content, debugging application errors.
guidance-author	agents/basecoat-50-security-guidance-author.agent.md	Uncategorized	specialized	claude-sonnet-4.6	—	BaseCoat guidance documentation author. USE FOR: creating security playbooks and best practices, authoring new instruction files and agent templates, writing skill documentation, drafting guidance framework updates. DO NOT USE FOR: incident response, operational tasks, code implementation.
guidance-reviewer	agents/basecoat-90-quality-guidance-reviewer.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when validating a BaseCoat guidance draft (instruction, skill, agent, prompt) before committing. Checks lint rules, required sections, frontmatter schema, and BaseCoat conventions. Returns a structured pass/fail verdict with actionable fixes.
ha-architect	agents/basecoat-10-core-ha-architect.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Design high-availability, resilience, and chaos testing strategies for distributed systems. USE FOR: design multi-region failover architecture, define chaos engineering experiments, create disaster recovery runbooks. DO NOT USE FOR: day-to-day incident response, cost optimization analysis.
Hardening Advisor	agents/basecoat-10-core-hardening-advisor.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	CIS Benchmarks and STIG hardening advisor for Dockerfiles, Kubernetes manifests, databases, and infrastructure configurations against security standards. USE FOR: harden Dockerfile against CIS benchmarks, audit Kubernetes manifests for STIG compliance, review infrastructure config security. DO NOT USE FOR: application code security review, live incident mitigation.
identity-architect	agents/basecoat-10-core-identity-architect.agent.md	Uncategorized	basic	gpt-5.3-codex	—	Identity and access architecture specialist. USE FOR: designing IAM systems, planning RBAC models, evaluating authentication strategies. DO NOT USE FOR: IAM implementation, directory administration.
incident-responder	agents/basecoat-60-workflow-incident-responder.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Structured incident response and recovery agent for classifying incidents, guiding mitigation, coordinating communications, verifying recovery, and facilitating post-incident learning. USE FOR: classify and triage active production incidents, guide on-call mitigation steps, facilitate post-incident retrospectives. DO NOT USE FOR: proactive security hardening, routine deployment tasks.
infrastructure-deploy	agents/basecoat-60-workflow-infrastructure-deploy.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Orchestrates Azure infrastructure deployments using Bicep, handles resource group management, parameter validation, and rollback strategies. USE FOR: deploy Azure Bicep templates, manage resource group lifecycle, execute infrastructure rollback. DO NOT USE FOR: application code deployments, cost analysis and optimization.
instruction-auditor	agents/basecoat-50-security-instruction-auditor.agent.md	Uncategorized	specialized	gpt-5.4-mini	—	Detects missing instruction coverage for a repo — identifies tech stacks and workflow patterns present in the codebase that have no corresponding BaseCoat instruction file in the overlay. USE FOR: find uncovered tech stacks in a repo overlay, audit BaseCoat instruction file gaps, identify missing workflow pattern coverage. DO NOT USE FOR: writing new instruction files, general code review.
issue-triage	agents/basecoat-10-core-issue-triage.agent.md	Uncategorized	basic	gpt-5.4-mini	—	Use when GitHub issues need systematic quality review and triage. USE FOR: detecting duplicates and invalid issues, verifying closed issues were actually resolved, enforcing label/type/priority standards, linking related issues and PRs, checking branch connections, proposing fixes, and ensuring titles are meaningful. DO NOT USE FOR: writing implementation code, managing PRs that are not issue-linked, or sprint capacity planning.
legacy-modernization	agents/basecoat-10-core-legacy-modernization.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Guides teams through Web Forms to Razor Pages migration using the strangler fig pattern for incremental modernization of legacy ASP.NET applications. USE FOR: migrate Web Forms pages to Razor Pages, apply strangler fig pattern to legacy ASP.NET apps, plan incremental .NET modernization. DO NOT USE FOR: greenfield application development, cloud infrastructure migration.
llmops	agents/basecoat-10-core-llmops.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	LLM operations and prompt engineering specialist. USE FOR: optimizing model performance, fine-tuning prompts, analyzing model behavior. DO NOT USE FOR: model training, infrastructure setup.
manual-test-strategy	agents/basecoat-90-quality-manual-test-strategy.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when you need a structured manual testing strategy for a feature or risk inventory. Produces a decision rubric, exploratory charter, regression checklist, defect template, and automation backlog. Automatically files GitHub Issues for automation candidates.
mcp-developer	agents/basecoat-10-core-mcp-developer.agent.md	Uncategorized	internal	claude-sonnet-4	—	MCP (Model Context Protocol) development specialist. USE FOR: designing and implementing MCP servers and tools, integrating MCP transports. DO NOT USE FOR: direct model interactions, non-MCP tasks.
memory-curator	agents/basecoat-10-core-memory-curator.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Cross-session memory and knowledge management curator. USE FOR: extracting and storing knowledge from long conversations, deduplicating learning across sessions, injecting relevant context into new conversations, managing memory decay and TTLs. DO NOT USE FOR: real-time conversation support, immediate decision-making, output formatting.
memory-promoter	agents/basecoat-10-core-memory-promoter.agent.md	Uncategorized	basic	claude-haiku-4.5	—	Analyzes session transcripts and sprint summaries to identify high-value patterns for promotion to long-term BaseCoat memory contributions. USE FOR: extract reusable patterns from session transcripts, identify conventions worth promoting to BaseCoat memory, review sprint summaries for learnings. DO NOT USE FOR: writing code or instructions directly, real-time session assistance.
merge-coordinator	agents/basecoat-10-core-merge-coordinator.agent.md	Uncategorized	basic	claude-haiku-4.5	—	Parallel branch merge coordinator. Use when multiple feature branches need to be merged into a target branch without interactive git editors hanging automated pipelines. Handles conflict detection, safe resolution, and ordered PR merging.
middleware-dev	agents/basecoat-10-core-middleware-dev.agent.md	Uncategorized	basic	gpt-5.3-codex	—	Middleware and integration development specialist. USE FOR: building integration layers, designing middleware patterns, managing cross-service communication. DO NOT USE FOR: frontend or backend-specific work.
mlops	agents/basecoat-30-ai-mlops.agent.md	Uncategorized	basic	gpt-5.3-codex	—	ML operations and model management specialist. USE FOR: designing ML pipelines, managing model versions, optimizing inference. DO NOT USE FOR: model training, data science.
new-customization	agents/basecoat-10-core-new-customization.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when creating or updating a customization asset such as an instruction, skill, prompt, or agent. Chooses the right primitive, authors the file, and validates frontmatter and placement.
Observability Engineer	agents/basecoat-10-core-observability-engineer.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	OpenTelemetry instrumentation, structured logging, distributed tracing, metrics taxonomy, and dashboard-as-code for operational excellence. USE FOR: instrument services with OpenTelemetry, design structured logging schema, build dashboard-as-code for metrics. DO NOT USE FOR: incident response triage, infrastructure provisioning.
orchestrator	agents/basecoat-10-core-orchestrator.agent.md	Uncategorized	advanced	claude-sonnet-4.6	—	Multi-agent orchestrator for complex, cross-domain tasks. USE FOR: decomposing large goals into subtasks, routing work to specialist agents, coordinating parallel execution, monitoring progress and escalating blockers, aggregating results. DO NOT USE FOR: simple single-agent tasks, real-time requirements, direct implementation.
orchestrator	agents/orchestrator.agent.md	Uncategorized	advanced	not-specified	—	Compatibility alias for the orchestrator agent. Preserves the legacy filename while the prefixed BaseCoat agent is the canonical source. USE FOR: routing multi-step workflows, coordinating parallel agents, tracking execution state. DO NOT USE FOR: single-step tasks, user-facing triage, direct tool calls.
orphaned-pr-cleanup	agents/basecoat-10-core-orphaned-pr-cleanup.agent.md	Uncategorized	specialized	gpt-5.4-mini	—	Use when identifying and resolving stale or orphaned pull requests that have no active owner, blocked reviews, or outdated mergeability status. USE FOR: detect PRs without recent activity, classify close/revive/merge candidates, request ownership reassignment, and produce cleanup actions with SLA windows. DO NOT USE FOR: code implementation work, deep architecture design, or replacing release governance decisions.
penetration-test	agents/basecoat-90-quality-penetration-test.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Security penetration testing specialist. USE FOR: designing penetration tests, identifying security vulnerabilities, generating security reports. DO NOT USE FOR: fixing vulnerabilities, incident response.
performance-analyst	agents/basecoat-10-core-performance-analyst.agent.md	Uncategorized	basic	gpt-5.3-codex	—	Performance analysis agent for profiling, load testing, and optimization. Use when evaluating application performance, planning load tests, analyzing Core Web Vitals, or investigating query and caching performance.
policy-as-code-compliance	agents/basecoat-50-security-policy-as-code-compliance.agent.md	Uncategorized	specialized	claude-sonnet-4.6	—	Policy-as-code compliance agent for validating code and configuration against organizational rules, managing exceptions, and producing audit-ready compliance reports. USE FOR: validate Terraform against OPA policies, generate compliance audit reports, manage policy exceptions. DO NOT USE FOR: writing application business logic, live incident response.
product-manager	agents/basecoat-10-core-product-manager.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when gathering requirements, writing user stories, defining acceptance criteria, planning roadmaps, or prioritizing features using frameworks like RICE or MoSCoW.
production-readiness	agents/basecoat-10-core-production-readiness.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Production Readiness Agent for ensuring applications meet operational requirements before release; coordinates BCP/DRP, incident response, and safety analysis. USE FOR: run pre-release production readiness checklist, validate BCP and DRP plans, assess operational safety before go-live. DO NOT USE FOR: feature development, post-incident root cause analysis.
program-bootstrap	agents/program-bootstrap.agent.md	Uncategorized	advanced	claude-sonnet-4.6	—	Thin orchestration entrypoint for end-to-end startup pack generation. USE FOR: bootstrapping a new program with coordinated onboarding/backlog/spec/architecture/workflow outputs, running dry-run orchestration before writing artifacts, resuming partially completed orchestration with checkpoints, preserving repo-specific delivery labels while normalizing governance labels. DO NOT USE FOR: replacing specialist agents, forcing one repo taxonomy, direct single-step authoring that a specialist agent already handles.
project-onboarding	agents/basecoat-10-core-project-onboarding.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Single-invocation new repo setup with BaseCoat integration. Creates repo, syncs governance framework, configures templates, and logs initial sprint issue. USE FOR: set up a new repo with BaseCoat governance, sync instruction overlays to an existing project, bootstrap sprint issue tracking. DO NOT USE FOR: onboarding individual developers, migrating existing codebases.
prompt-coach	agents/basecoat-10-core-prompt-coach.agent.md	Uncategorized	basic	gpt-5.3-codex	—	Use when reviewing prompts, scoring prompt quality, identifying anti-patterns, and guiding iterative refinement of LLM prompts.
prompt-engineer	agents/basecoat-10-core-prompt-engineer.agent.md	Uncategorized	basic	gpt-5.3-codex	—	Prompt optimization and system prompt engineering agent. Use when designing system prompts, optimizing token usage, crafting few-shot examples, or structuring chain-of-thought instructions.
rca	agents/basecoat-10-core-rca.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Root Cause Analysis agent for deep-dive incident investigations, hypothesis testing, and prevention follow-up. USE FOR: run post-incident root cause analysis, trace production outage to contributing factors, generate 5-why analysis report. DO NOT USE FOR: live incident triage and containment, general performance tuning.
release-freeze-enforcer	agents/basecoat-60-workflow-release-freeze-enforcer.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when enforcing release freeze windows, routing exception requests, and coordinating branch access during a freeze. USE FOR: evaluate freeze exceptions, block unauthorized merge attempts, and publish go/no-go decisions for frozen branches. DO NOT USE FOR: merging changes, bypassing approvals, or resolving code conflicts.
release-impact-advisor	agents/basecoat-60-workflow-release-impact-advisor.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Assesses release readiness, change impacts, blast radius, rollback planning, and safe deployment strategies with canary deployments, feature flags, and changelog generation. USE FOR: assess release blast radius, plan rollback strategy, recommend deployment approach. DO NOT USE FOR: executing deployments, live incident response.
release-manager	agents/basecoat-60-workflow-release-manager.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Automated versioned release workflow. Reads merged PRs since the last release, bumps version.json, writes CHANGELOG entry, creates git tag, and publishes GitHub release. USE FOR: bump semver and publish GitHub release, generate changelog from merged PRs, create git release tag. DO NOT USE FOR: sprint planning, deployment risk assessment.
release-readiness-chair	agents/basecoat-60-workflow-release-readiness-chair.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when facilitating release readiness ceremonies and making explicit go/no-go decisions. USE FOR: collect release evidence across quality, operations, and rollback readiness; identify unresolved launch risks; enforce gate criteria; and publish decision records with owners and due dates. DO NOT USE FOR: implementing feature code, replacing incident response command, or product roadmap planning.
replanning-engine	agents/basecoat-10-core-replanning-engine.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when S2 assessment data shows the work is far larger than estimated and a replanning decision is needed. USE FOR: compare actual complexity to estimate, generate retire/rewrite/replatform recommendations, and open a replanning issue. DO NOT USE FOR: routine triage or deployment execution.
Resilience Reviewer	agents/basecoat-90-quality-resilience-reviewer.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Code-level resilience pattern review — circuit breakers, timeouts, bulkhead isolation, graceful degradation, retry logic, and load shedding implementation. USE FOR: review circuit breaker and retry patterns in code, audit timeout hierarchy, validate graceful degradation. DO NOT USE FOR: live incident response, infrastructure capacity planning.
retro-facilitator	agents/basecoat-60-workflow-retro-facilitator.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	End-of-sprint retrospective agent. Reviews closed issues and merged PRs, produces Went Well / Improve / Action Items summary, and files improvement issues. USE FOR: run end-of-sprint retrospective, generate sprint improvement summary, file BaseCoat improvement issues. DO NOT USE FOR: planning next sprint, velocity estimation.
rollout-basecoat	agents/basecoat-60-workflow-rollout-basecoat.agent.md	Uncategorized	basic	claude-haiku-4.5	—	Use when onboarding a repository to BaseCoat in an enterprise setting. Focuses on pinned versions, safe rollout, installation method, and validation steps.
run-history-cleanup	agents/basecoat-60-workflow-run-history-cleanup.agent.md	Uncategorized	basic	gpt-5.4-mini	—	Cleans GitHub Actions workflow run history safely by deleting stale, completed runs according to retention policy while preserving evidence for active incidents and compliance windows. USE FOR: pruning old completed workflow runs, reducing run-history noise, enforcing run-retention policy, and producing a cleanup report. DO NOT USE FOR: deleting in-progress runs, deleting runs tied to active incidents, changing workflow YAML retention-days, or bypassing compliance retention rules.
s4-shadow-mode-validator	agents/basecoat-10-core-s4-shadow-mode-validator.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when comparing shadow-mode and live behavior during S4 soak before cutover. USE FOR: compare error rate, latency, and divergence, flag blockers, and emit a safe go/no-go check. DO NOT USE FOR: state curation or general monitoring.
Secrets Manager	agents/basecoat-50-security-secrets-manager.agent.md	Uncategorized	specialized	claude-sonnet-4.6	—	Secrets lifecycle management — discovery, rotation, expiry scanning, emergency revocation, and Vault patterns for infrastructure and application secrets. USE FOR: plan secrets rotation schedule, scan for expiring credentials, execute emergency revocation. DO NOT USE FOR: detecting hardcoded secrets in code, general performance optimization.
Security Monitor	agents/basecoat-50-security-security-monitor.agent.md	Uncategorized	specialized	gpt-5.4-mini	—	Detection engineering and SIEM configuration — maps MITRE ATT&CK tactics to detection rules, builds alerting baselines, and operationalizes NIST CSF Detect. USE FOR: build ATT&CK-mapped detection rules, calibrate SIEM alert thresholds, map compliance to detection coverage. DO NOT USE FOR: live incident response, secrets rotation.
security-analyst	agents/basecoat-50-security-security-analyst.agent.md	Uncategorized	specialized	gpt-5.3-codex	—	Security analysis and threat assessment specialist. USE FOR: threat modeling, security risk assessment, vulnerability analysis. DO NOT USE FOR: incident response, remediation.
security-operations	agents/basecoat-50-security-security-operations.agent.md	Uncategorized	specialized	claude-sonnet-4.6	—	Provide SOC (Security Operations Center) playbook guidance for threat detection, incident response, secrets rotation, audit logging, and operational security. USE FOR: run SOC incident response playbook, triage security alerts, coordinate credential rotation post-breach. DO NOT USE FOR: building SIEM detection rules, code-level security review.
self-healing-ci	agents/basecoat-60-workflow-self-healing-ci.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Automated CI failure analysis, log parsing, and pipeline remediation with retry strategies, flaky test detection, dependency resolution, and cache invalidation. USE FOR: auto-remediate CI failures, quarantine flaky tests, resolve build dependency and cache errors. DO NOT USE FOR: designing CI pipeline architecture, code-level debugging.
solution-architect	agents/basecoat-10-core-solution-architect.agent.md	Uncategorized	basic	claude-sonnet-4-5	—	Solution architecture agent for system design, C4 diagrams, ADRs, technology selection, and cross-cutting concerns. Use when designing new systems, evaluating technology choices, or reviewing architecture for scalability and risk.
sprint-closeout-auditor	agents/basecoat-50-security-sprint-closeout-auditor.agent.md	Uncategorized	specialized	gpt-5.4-mini	—	Use when closing a sprint and validating completion evidence before planning the next sprint. USE FOR: verify merged PR coverage, confirm CI health, identify unresolved errors and open issues, check test evidence, and produce carry-forward actions with owners. DO NOT USE FOR: writing feature code, replacing incident postmortems, or long-term roadmap prioritization.
sprint-planner	agents/basecoat-10-core-sprint-planner.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Goal-to-issues decomposition and wave dependency mapping. Accepts a sprint goal, produces GitHub issues with labels, wave dependency maps, agent assignments, and acceptance criteria. USE FOR: decompose sprint goal into GitHub issues, build wave dependency map, assign agent roles. DO NOT USE FOR: running sprint retrospectives, story point estimation.
sprint-project-mapper	agents/basecoat-10-core-sprint-project-mapper.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when issues/PRs need clustering into meaningful sprint/project groups and rollup metrics for planning or release notes. USE FOR: grouping by sprint/wave/tags, computing issue-PR-LOC-cycle-time metrics, validating group size significance, and producing release-note-ready summaries. DO NOT USE FOR: code implementation, CI/CD deployment, or one-off issue editing.
sprint-retrospective	agents/basecoat-10-core-sprint-retrospective.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Reconstructs repository history for sprint retrospectives, generating structured markdown with metrics, timelines, and actionable development tips. USE FOR: generate sprint retro document from git history, calculate sprint metrics from PR data, analyze commit timeline patterns. DO NOT USE FOR: planning next sprint, filing improvement issues.
sre-engineer	agents/basecoat-10-core-sre-engineer.agent.md	Uncategorized	basic	gpt-5.3-codex	—	Site reliability engineering agent for SLOs, error budgets, incident response, chaos engineering, and toil reduction. Use when improving service reliability and resilience.
station-bottleneck-analyzer	agents/basecoat-10-core-station-bottleneck-analyzer.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when analyzing takt-time JSON to compute queue length and throughput by station, rank bottlenecks, and file the weekly bottleneck report issue. USE FOR: station-level queue pressure, throughput trends, weekly issue filing, and follow-up actions. DO NOT USE FOR: dispatching work or changing replanning policy.
strategy-to-automation	agents/basecoat-10-core-strategy-to-automation.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when converting manual test paths into automation candidates. Maps paths to smoke tests, regression tiers, or agent specs. ALWAYS files a GitHub Issue for every automation candidate identified.
supply-chain-security	agents/basecoat-50-security-supply-chain-security.agent.md	Uncategorized	specialized	claude-sonnet-4.6	—	Secure software supply chain with artifact signing, SBOM generation, and provenance tracking. USE FOR: generate SBOM for a release build, sign artifacts with Sigstore and verify provenance, assess and improve SLSA compliance level. DO NOT USE FOR: general dependency vulnerability scanning, runtime security monitoring.
takt-time-tracker	agents/basecoat-10-core-takt-time-tracker.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when measuring dwell time at each station and flagging SLA breaches. USE FOR: compute median and p95 time at S1-S5, identify bottlenecks, and export dashboard-ready JSON. DO NOT USE FOR: dispatching work or making replanning decisions.
task-scope-validator	agents/basecoat-60-workflow-task-scope-validator.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Task scope validator for sub-agent dispatch. Analyzes task prompts to detect overscope, ambiguity, and risk before forwarding to explore, task, or general-purpose agents. USE FOR: validate task prompts pre-dispatch, classify tasks as automatable/gather-only/defer, identify scope refinement needs. DO NOT USE FOR: executing tasks, writing implementation code, or modifying task prompts without user feedback.
tech-writer	agents/basecoat-10-core-tech-writer.agent.md	Uncategorized	basic	claude-sonnet-4.6	—	Use when creating or improving technical documentation, API docs, runbooks, tutorials, ADRs, changelogs, or implementing docs-as-code workflows.
ux-designer	agents/basecoat-10-core-ux-designer.agent.md	Uncategorized	basic	claude-sonnet-4-5	—	UX design agent for user journey mapping, wireframe specs, component design, and accessibility audits. Use when designing user experiences, evaluating usability, or auditing interfaces for WCAG compliance.

Skills

Skill	Directory	Visibility	Trigger Conditions	Templates
agent-design	skills/agent-design/	public	design a new Copilot agent, scaffold a skill folder, create an instruction file, choose agent vs skill vs instruction, author agent frontmatter and conventions.	agent-template.md, instruction-template.md, skill-template.md
agentic-sdlc-autonomy	skills/agentic-sdlc-autonomy/	public	agentic SDLC governance, PR risk classification (A0-A5), auto-merge policy, merge queue gates, deployment lane policy, DB migration controls, IaC safety rules, runner isolation, production approval flows, and policy-versus-settings drift.	workflow-only
agentops-audit	skills/agentops-audit/	public	scoring spec quality, identifying concrete fixes, producing revised specs, validating cost/latency fit, generating routing profiles.	workflow-only
api-audit	skills/api-audit/	public	reviewing API endpoint definitions, validating request/response contracts, assessing error handling patterns, evaluating versioning strategies, analyzing documentation completeness.	workflow-only
api-design	skills/api-design/	public	design a REST API contract, review an OpenAPI diff for breaking changes, choose an API versioning strategy, draft GraphQL schema changes, create a deprecation or sunset plan.	api-governance-checklist.md, breaking-change-checklist.md, openapi-template.md, versioning-decision-tree.md
api-security	skills/api-security/	public	secure JWT authentication for an API, add rate limiting to endpoints, review API authorization flaws, harden GraphQL queries and mutations, prevent SQL injection in API handlers.	workflow-only
app-inventory	skills/app-inventory/	public	inventory a legacy application portfolio, scan app dependencies and connection strings, assess migration complexity for an app, create an application inventory report, map external service bindings before modernization.	complexity-scoring-template.md, inventory-report-template.md
architecture	skills/architecture/	public	design a system architecture, create a C4 diagram, write an ADR for a platform choice, compare technology options with a matrix, assess architectural risks and mitigations.	adr-template.md, c4-diagram-template.md, risk-register-template.md, tech-selection-matrix-template.md
azure-container-apps	skills/azure-container-apps/	public	deploy an app to Azure Container Apps, configure a Dapr sidecar, set Azure Container Apps scaling rules, manage revisions and traffic splitting, create a container apps job.	workflow-only
azure-devops-rest	skills/azure-devops-rest/	public	query Azure DevOps work items via REST, trigger a pipeline run from a script, paginate Azure DevOps API results, authenticate with PAT or System.AccessToken, update a work item with JSON Patch.	workflow-only
azure-identity	skills/azure-identity/	public	assign Azure RBAC roles, configure managed identity for an app, create an Entra ID app registration, set up GitHub OIDC federation, design a conditional access policy.	app-registration-checklist.md, conditional-access-policy-template.md, managed-identity-mapping-template.md, rbac-role-assignment-template.md, workload-identity-federation-template.md
azure-identity-audit	skills/azure-identity-audit/	public	audit RBAC assignments, managed identity scope, app registration permissions, OIDC federation, least privilege.	workflow-only
azure-landing-zone	skills/azure-landing-zone/	public	design an Azure landing zone, scaffold a management group hierarchy, create a hub networking platform subscription, assign a regulatory policy initiative, vend a new application landing zone.	adr-template.md
azure-linux-app-service	skills/azure-linux-app-service/	public	deploy a Flask or FastAPI app to App Service Linux, configure a startup command for a Node app, set up a deployment slot swap, stream Azure App Service logs, choose between code deploy and container deploy.	workflow-only
azure-networking	skills/azure-networking/	public	design a hub-spoke VNet topology, set up private endpoints and Private DNS zones, author an NSG rule matrix, create forced-tunneling route tables, review hybrid connectivity on Azure.	templates/cidr-allocation.md, templates/hub-spoke-topology.md, templates/nsg-rule-matrix.md, templates/private-endpoint-dns-zones.md
azure-policy	skills/azure-policy/	public	write an Azure Policy to require tags, create a policy initiative for CIS controls, build a DeployIfNotExists remediation, generate a KQL compliance dashboard query, restrict allowed VM SKUs.	compliance-report-template.md, initiative-definition-template.md, policy-definition-template.md, remediation-task-template.md
azure-policy-audit	skills/azure-policy-audit/	public	audit policy coverage, remediation completeness, exemption hygiene, policy drift, compliance reporting.	workflow-only
azure-waf-review	skills/azure-waf-review/	public	run an Azure Well-Architected review, score a workload across WAF pillars, review Terraform or Bicep for reliability and security gaps, prioritize remediation actions, assess an architecture before production.	pillar-scoring-rubric.md, remediation-action-plan-template.md, waf-assessment-report-template.md
backend-audit	skills/backend-audit/	public	reviewing backend implementations, analyzing code quality, assessing test coverage, identifying performance bottlenecks, security vulnerabilities, structural debt.	workflow-only
backend-dev	skills/backend-dev/	public	implement a REST endpoint, scaffold a service layer, define an error response catalog, add repository pattern data access, review backend logic for correctness.	api-spec-template.md, error-catalog-template.md, repository-pattern-template.md, service-template.md
backlog-burndown	skills/backlog-burndown/	public	build burn-down tables from issue and open-PR state changes, detect spillover risk from velocity and remaining scope, prioritize blockers to protect sprint goals, and produce daily backlog status updates with explicit actions.	workflow-only
basecoat	skills/basecoat/	public	find the right BaseCoat agent, browse the BaseCoat agent catalog, route a prompt to backend-dev, discover which agent handles code review, delegate a task to the right discipline.	workflow-only
bom-schema	skills/bom-schema/	internal	JSON schema for BOM validation, required-field checks, and template creation.	workflow-only
bom-validation	skills/bom-validation/	internal	validating BOM completeness before S2, detecting circular dependencies, enforcing CAF naming compliance, checking registry references before handoff.	workflow-only
build-failure-triage	skills/build-failure-triage/	internal	identify first failing stage, map log signatures to likely causes, recommend smallest safe fix path, and produce validation checklist for CI and local runs.	workflow-only
build-master-control-plane	skills/build-master-control-plane/	internal	lane-state policy, break-fix eligibility, retry/revert thresholds, and escalation rules.	workflow-only
change-isolation	skills/change-isolation/	public	define path-based lane boundaries, isolate deploy workflows by layer, design independent versioning lanes, audit cross-trigger coupling in GitHub Actions, create release lane contracts.	layer-boundary-matrix-template.md, release-lane-contract-template.md, workflow-path-filter-checklist.md
ci-audit	skills/ci-audit/	public	exporting branch protection and required checks, verifying merge queue and environment protections, auditing runners and security gates, and reporting policy-vs-live gaps.	templates/audit-findings-template.md, templates/recommendations-template.md
ci-flake-quarantine	skills/ci-flake-quarantine/	internal	confirm flakiness, quarantine only after repeat evidence, and produce owner/expiry tracking.	workflow-only
code-review	skills/code-review/	public	review pull request for bugs, inspect diff for regression risk, identify missing test coverage, rank review findings by severity, review refactor for edge cases.	workflow-only
container-build-assessment	skills/container-build-assessment/	public	Assess Docker build readiness with composable scripts that analyze Dockerfile structure, inspect dependency footprint, estimate image size, and report security posture in structured JSON suitable for automation and remediation planning.	workflow-only
container-migration	skills/container-migration/	public	containerize this legacy app, create a Dockerfile for production, migrate app to Azure Container Apps, add Kubernetes manifests and health checks, set up ACR build and push workflow.	workflow-only
contract-testing	skills/contract-testing/	public	add Pact contract tests between services, verify provider won't break consumers, set up Pact Broker in CI, orchestrate multi-service integration tests with Docker Compose, add mutation testing gate for APIs.	workflow-only
copilot-usage-analytics	skills/copilot-usage-analytics/	public	estimate Copilot session cost, analyze expensive agent dispatches, recommend cheaper model routing, audit Copilot workflow token usage, document GitHub Copilot usage APIs.	templates/api-landscape.md, templates/model-routing-recommendation-template.md, templates/session-cost-estimate-template.md, templates/usage-report.md
cqrs-event-sourcing	skills/cqrs-event-sourcing/	public	design CQRS architecture for a service, implement event sourcing for audit history, separate command and query models, plan read model projections and replay, add saga orchestration for eventual consistency.	workflow-only
create-instruction	skills/create-instruction/	public	create a new instructions file, choose applyTo glob for an instruction, write guardrails for a coding workflow, add repository standards for a language, draft instruction frontmatter and naming.	templates/instruction.template.md
create-skill	skills/create-skill/	public	add a new SKILL.md file, design skill trigger phrases, decide if work belongs in a skill, scaffold skill folder with templates, write discovery-focused skill frontmatter.	templates/SKILL.template.md
cross-stack-modernization	skills/cross-stack-modernization/	public	plan legacy app modernization strategy, choose rewrite versus refactor versus replace, design strangler fig migration, sequence service extraction by dependency risk, decide database-first or UI-first migration.	workflow-only
data-tier	skills/data-tier/	public	design a relational schema, write migration with rollback support, review SQL for N+1 or missing indexes, build a data dictionary, define repository or data access patterns.	data-dictionary-template.md, migration-template.md, query-review-checklist.md, schema-design-template.md
data-tier-audit	skills/data-tier-audit/	public	audit schema drift, migration rollback safety, index health, query risk, repository patterns.	workflow-only
database-migration	skills/database-migration/	public	plan expand-contract schema migration, design blue-green database cutover, write Flyway versioned migration and undo scripts, prepare rollback plan for production schema change, validate zero-downtime database release process.	workflow-only
decision-log-capture	skills/decision-log-capture/	internal	document decision, rationale, options considered, owner, and follow-up actions from standup, sprint, and release ceremonies.	workflow-only
dependency-blocker-monitoring	skills/dependency-blocker-monitoring/	internal	dependency maps, cell health checks, blocker issue creation, and recovery closures.	workflow-only
dev-containers	skills/dev-containers/	public	create devcontainer.json for this repo, set up Codespaces for contributors, containerize local dev toolchain, add VS Code extensions inside container, make development setup reproducible across machines.	workflow-only
devops	skills/devops/	public	create GitHub Actions pipeline, review Bicep or Terraform deployment templates, define release promotion gates, write rollback runbook for a service, add monitoring and health checks for deployment.	deployment-checklist.md, environment-promotion-template.md, github-actions-template.md, rollback-runbook-template.md
devops-audit	skills/devops-audit/	public	reviewing GitHub Actions workflows, analyzing deployment processes, validating environment configurations, assessing automation completeness, identifying workflow bottlenecks.	workflow-only
docs-site	skills/docs-site/	public	create a docs site for this repo, set up MkDocs Material, publish documentation to GitHub Pages, generate getting-started docs with diagrams, add docs CI workflow.	workflow-only
documentation	skills/documentation/	public	write a project README, record an architecture decision, create an operational runbook, review docs for accuracy and gaps, establish docs-as-code standards.	adr-template.md, readme-template.md, runbook-template.md
domain-driven-design	skills/domain-driven-design/	public	model bounded contexts and aggregates, design domain events and invariants, apply DDD to microservice boundaries, implement saga orchestration for business workflows, combine DDD with CQRS patterns.	workflow-only
dotnet-modernization	skills/dotnet-modernization/	public	inventory a legacy .NET solution, plan phased .NET upgrade, review NuGet and framework compatibility, define modernization test and release gates, remediate breaking changes during migration.	workflow-only
e2e-testing	skills/e2e-testing/	public	choose between Playwright and Cypress, reduce flaky browser tests, test login or checkout journeys, set up cross-browser CI coverage, plan E2E fixtures and mocks.	workflow-only
electron-apps	skills/electron-apps/	public	secure Electron IPC design, preload script API patterns, package and sign desktop app, implement auto-update flow, review BrowserWindow security settings.	workflow-only
entity-framework-migration	skills/entity-framework-migration/	public	migrate EF6 to EF Core, refactor DbContext configuration, convert model mappings and conventions, plan phased database cutover, validate query compatibility after migration.	workflow-only
environment-audit-drift	skills/environment-audit-drift/	public	scheduled drift audits in CI, pre-deployment drift gates, identifying branch-protection mismatches to autonomy levels, and producing remediation-first findings for operators.	README.md
environment-bootstrap	skills/environment-bootstrap/	public	set up GitHub Actions OIDC to Azure, provision Terraform state storage, configure Key Vault for CI/CD secrets, design dev-to-prod environment promotion, grant Fabric workspace service principal access.	workflow-only
escalation-routing	skills/escalation-routing/	internal	release signoff, irreversible changes, compliance gates.	workflow-only
factory-state-machine	skills/factory-state-machine/	internal	intake/complete/pending transitions, auto-proceed rules, escalation checks, and state validation.	workflow-only
failure-pattern-process	skills/failure-pattern-process/	internal	evidence mining, append-only raw finding capture, common-versus-local triage with rationale, and prioritized enhancement planning with early-detection gates.	checklists/gate-validation-checklist.md, templates/early-detection-gates-template.md, templates/enhancement-backlog-template.md, templates/raw-findings-log-template.md, templates/run-summary-template.md, templates/source-index-template.md, templates/triage-matrix-template.md
flow-admission-control	skills/flow-admission-control/	public	WIP limit policy, merge-ready admission criteria, stale PR expiration rules, and load-shedding strategy.	workflow-only
flow-audit	skills/flow-audit/	public	merge queue bottleneck scans, stale PR analysis, CI waste detection, throughput baseline creation, and severity-ranked findings.	workflow-only
flow-optimize	skills/flow-optimize/	public	flow optimization roadmaps, CI tier tuning, merge policy improvements, and KPI-target planning.	workflow-only
flow-suggest	skills/flow-suggest/	public	remediation prioritization, high-confidence auto-issue creation, issue drafting, acceptance-criteria definition, and execution-wave planning.	workflow-only
flow-track	skills/flow-track/	public	trend scorecards, regression alerts, threshold monitoring, and action recommendations tied to metrics.	workflow-only
frontend-audit	skills/frontend-audit/	public	audit generated UI, review a PR for WCAG or responsive issues, verify interaction states and copy consistency, check performance-sensitive patterns.	workflow-only
frontend-dev	skills/frontend-dev/	public	scaffold accessible UI component, review page for WCAG issues, design frontend state management, implement responsive layout behavior, audit frontend performance and correctness.	accessibility-checklist.md, component-spec-template.md, state-management-template.md
git-worktrees	skills/git-worktrees/	public	create isolated workspace for feature branch, run parallel tasks without stashing, set up clean environment for risky experiment, manage multiple branches simultaneously, clean up stale worktrees.	workflow-only
github-security-posture	skills/github-security-posture/	public	review branch protection and rulesets, check secret scanning and push protection, triage Dependabot or code scanning alerts, assess CODEOWNERS coverage, produce GitHub security posture report.	posture-report-template.md
gitops	skills/gitops/	public	set up Flux or ArgoCD workflow, structure multi-environment cluster config, handle Kubernetes drift reconciliation, choose GitOps secrets pattern, review pull-based deployment practices.	workflow-only
governance	skills/governance/	public	common-vs-specific policy docs, canonical label contracts, migration maps, template guidance, and governance issue planning.	workflow-only
governance-audit	skills/governance-audit/	public	issue and PR metadata audits, canonical-label drift checks, missing governance doc detection, and follow-up issue planning.	workflow-only
ha-resilience	skills/ha-resilience/	public	design multi-region failover, add retry and jitter strategy, introduce circuit breaker for flaky dependency, plan chaos testing against SLOs, define health probes and recovery behavior.	workflow-only
handoff	skills/handoff/	public	create end-of-session handoff, transfer task between agents, summarize unfinished work with next steps, capture commands and validations run, package follow-up deployment context.	handoff-template.md
human-in-the-loop	skills/human-in-the-loop/	public	add approval step before production deploy, define escalation triggers for risky automation, design asynchronous human review workflow, defer destructive action pending approval, document graceful degradation when reviewers are unavailable.	workflow-only
identity-migration	skills/identity-migration/	public	migrate ASP.NET Membership users, preserve legacy password verification, integrate Entra ID OIDC with Identity, convert roles to claims, plan hybrid local and Entra authentication.	workflow-only
infrastructure-audit	skills/infrastructure-audit/	public	reviewing IaC code quality, validating resource configurations, assessing networking architecture, identifying security misconfigurations, analyzing cost optimization opportunities.	workflow-only
issue-triage	skills/issue-triage/	public	backlog hygiene and duplicate detection, validating closed issues have resolution evidence, enforcing label/type/priority conventions, auditing titles and relationships.	workflow-only
landing-zone-audit	skills/landing-zone-audit/	public	audit landing zone designs, verify hierarchy and platform subscriptions, check policy baseline coverage, review vending readiness.	workflow-only
lexicon	skills/lexicon/	public	create project lexicon file, audit docs for terminology drift, define naming taxonomy for assets, detect off-brand tone or vibe mismatches, standardize canonical product terms.	audit-checklist.md, lexicon-template.md
manual-test-strategy	skills/manual-test-strategy/	public	classify manual versus automated coverage, create exploratory test charter, build repeatable manual regression checklist, capture defect evidence for triage, identify automation candidates from manual testing.	charter-template.md, checklist-template.md, defect-template.md, rubric-template.md
mcp-audit	skills/mcp-audit/	public	reviewing MCP server code quality, validating tool definitions, assessing schema compliance, identifying integration issues, evaluating error handling.	workflow-only
mcp-development	skills/mcp-development/	public	scaffold MCP server, define MCP tool contract, configure MCP transport, review MCP server security, integrate MCP server with client.	mcp-server-template.md, tool-definition-template.md, transport-config-template.md
memory-promoter	skills/memory-promoter/	public	extract recurring fix patterns, rank memory candidates by frequency and impact, produce contribution-ready memory payloads, filter ephemeral or secret content before memory submission.	memory-candidate-scorecard-template.md, memory-payload-template.md
merge-conflict-mediator	skills/merge-conflict-mediator/	internal	classify conflict types, choose a merge policy, and hand a resolution plan to merge-coordinator.	workflow-only
observability	skills/observability/	public	instrument service with OpenTelemetry, add structured logging and trace IDs, define SLI or latency metrics, trace requests across queues and APIs, improve incident debugging telemetry.	otel-instrumentation.md
operation-context-resolver	skills/operation-context-resolver/	public	resolving preview/dev/staging/prod target before troubleshooting or deployment, enforcing allowed and blocked action checks, applying incident-readonly routing, validating human approval requirements for risky actions.	README.md
orphaned-pr-triage	skills/orphaned-pr-triage/	internal	identify orphaned PRs by inactivity windows, classify revive/close/escalate actions, draft maintainer comments for ownership handoff, and produce weekly cleanup reports with metrics.	workflow-only
penetration-testing	skills/penetration-testing/	public	test for SQL injection or SSRF, run OWASP Top 10 web assessment, validate broken access control, reproduce API auth bypass, write penetration test findings report.	owasp-testing-guide-map.md, pre-engagement-checklist.md, re-test-verification-checklist.md, remediation-tracker-template.md, vulnerability-report-template.md
performance-profiling	skills/performance-profiling/	public	profile hot path in service, compare baseline vs optimized runtime, find CPU or memory bottleneck, investigate slow database or I/O path, verify performance regression fix.	workflow-only
production-readiness	skills/production-readiness/	public	run production readiness review, check rollback and canary plan, assess disaster recovery readiness, review incident response runbooks, evaluate release go-live checklist.	workflow-only
public-safe-sanitization	skills/public-safe-sanitization/	internal	sanitizing roadmap/issue notes for sharing, redacting private URLs/customer names/IDs, producing public-safe summaries with redaction ledger, rewriting internal details into generic guidance.	workflow-only
receiving-code-review	skills/receiving-code-review/	public	address PR review comments, respond to code review feedback, categorize review items, re-request review after changes, resolve review threads.	workflow-only
refactoring	skills/refactoring/	public	extract large method safely, remove duplication without changing outputs, split module responsibilities, rename confusing abstractions with tests, plan incremental cleanup of legacy code.	workflow-only
release-audit	skills/release-audit/	public	audit a release candidate, verify semver and changelog entries, check tag and release note completeness, review rollback readiness.	workflow-only
release-notes	skills/release-notes/	public	create release notes for a version, summarize changes since a tag, generate notes by wave/sprint labels, produce internal or customer-facing changelog drafts, and structure upgrade notes with traceability.	workflow-only
rollout-basecoat	skills/rollout-basecoat/	public	refresh basecoat, update basecoat in a consumer repo, run sync.ps1 or sync.sh with .basecoat.yml defaults, verify installed basecoat version after sync, recover when rollout-basecoat skill invocation fails.	workflow-only
s4-deployment-checklist	skills/s4-deployment-checklist/	internal	checklist-driven release gating, rollback testing, monitoring readiness, and team briefing.	deployment-checklist.md
s4-rollback-testing	skills/s4-rollback-testing/	internal	building repeatable rollback rehearsal workflows, verifying rollback activation after soak windows, sequencing deploy/wait/rollback/verify/smoke-test steps, documenting drill outcomes for readiness checks.	workflow-only
security	skills/security/	public	run OWASP security review, create STRIDE threat model, scan for hardcoded secrets, audit dependencies for CVEs, write structured vulnerability report.	dependency-audit-template.md, owasp-api-security-checklist.md, owasp-checklist.md, stride-threat-model-template.md, vulnerability-report-template.md
security-operations	skills/security-operations/	public	write SIEM or KQL detection rules, automate secret rotation workflow, centralize security audit logs, build security alert triage playbook, monitor cloud or Kubernetes threats.	workflow-only
service-bus-migration	skills/service-bus-migration/	public	map MSMQ queues to topics and subscriptions, design hybrid bridge for zero-downtime cutover, convert binary messages to JSON, implement retry and dead-letter handling, plan Service Bus migration phases.	workflow-only
skill-scripts	skills/skill-scripts/	public	Use when a skill needs executable multi-step workflows where each script produces structured JSON that is passed to the next step, enabling composable assessment, planning, validation, and execution with clear contracts.	workflow-only
sprint-closeout	skills/sprint-closeout/	public	run closeout checklist across goals, completed work, spillover items, and unresolved blockers; produce release notes inputs and stakeholder summary; capture carry-forward actions with owners and due dates; and package evidence for retrospective and planning.	workflow-only
sprint-closeout-audit	skills/sprint-closeout-audit/	internal	run end-of-sprint completion checklist, validate carry-forward decisions, produce closeout report for leadership, and gate next-sprint planning until closure criteria are explicit.	workflow-only
sprint-management	skills/sprint-management/	public	plan sprint capacity and goals, run backlog grooming session, prepare sprint review agenda, track velocity against commitments, facilitate sprint ceremony workflow.	backlog-grooming-template.md, retrospective-template.md, sprint-planning-template.md
sprint-planner	skills/sprint-planner/	public	sprint goal decomposition, wave/dependency planning, issue breakdown planning, and next-sprint commitment shaping.	workflow-only
sprint-project-mapper	skills/sprint-project-mapper/	public	clustering by sprint/wave/project tags, split-vs-merge debate, and release-note metric rollups.	workflow-only
sprint-retrospective	skills/sprint-retrospective/	public	create sprint retrospective document, summarize merged PR and issue metrics, analyze time-to-merge trends, identify rework or PR size patterns, produce improvement actions from sprint data.	workflow-only
standup-signal-extraction	skills/standup-signal-extraction/	internal	convert updates into blockers/actions/dependencies, prioritize escalations, and produce owner-based daily execution plans.	workflow-only
station-bottleneck-analyzer	skills/station-bottleneck-analyzer/	internal	station-level queue pressure, throughput trends, bottleneck ranking, and weekly issue filing.	workflow-only
supply-chain-security	skills/supply-chain-security/	public	sign container image with Cosign, generate CycloneDX or SPDX SBOM, add SLSA provenance to GitHub Actions, scan dependencies and images for vulnerabilities, verify release artifact integrity.	workflow-only
takt-time-measurement	skills/takt-time-measurement/	internal	workflow templates, takt calculations, and metric export guidance.	workflow-only
task-decomposition	skills/task-decomposition/	public	split large tasks into smaller async work items, decide if work is automatable vs research vs deferred, validate sub-agent prompts for clarity, design task decomposition workflows.	automation-fitness-matrix.md, complex-task-breakdown-template.md, examples/example-1-api-feature.md, examples/example-2-refactoring.md, examples/example-3-system-redesign.md, examples/README.md, prompt-validation-checklist.md
tech-debt	skills/tech-debt/	public	build technical debt register, rank cleanup work with RICE, reserve sprint capacity for remediation, compare debt items by impact and effort, track debt amortization over time.	workflow-only
twelve-factor	skills/twelve-factor/	public	move config from code to environment, check stateless process design, separate build release and run stages, verify logs go to stdout, assess dev and prod parity.	workflow-only
ux	skills/ux/	public	map end-to-end user journey, create wireframe spec for new screen, review component states and interactions, run WCAG accessibility audit, evaluate usability of a workflow.	accessibility-audit-checklist.md, component-spec-template.md, user-journey-template.md, wireframe-spec-template.md

Instructions

Instruction	File	Scope	Description
architecture	instructions/architecture.instructions.md	**/*	BaseCoat compatibility alias for architecture guidance. Preserves the legacy filename while the prefixed BaseCoat instruction is the canonical source.
basecoat-10-core-agent-behavior	instructions/basecoat-10-core-agent-behavior.instructions.md	**/*	Use when an agent is retrying work, revising the same change repeatedly, or deciding whether to continue versus escalate. Prevents infinite retry loops, edit thrashing, and repeated failed actions.
basecoat-10-core-agent-routing	instructions/basecoat-10-core-agent-routing.instructions.md	**/*	Use when deciding which agent tier to invoke for a task. Provides cost-aware, security-conscious agent routing to avoid mismatches between task requirements and agent capabilities.
basecoat-10-core-agents	instructions/basecoat-10-core-agents.instructions.md	agents/**/*.agent.md	Use when creating, updating, or reviewing agent definitions. Covers naming, structure, required sections, skill pairing, capability-based routing, model policy, and testing.
basecoat-10-core-architecture	instructions/basecoat-10-core-architecture.instructions.md	src/**,lib/**,app/**,packages/**,**/iac/**,docs/architecture/**,docs/adr/**,docs/api/**	Use when making architectural decisions, designing APIs, creating system diagrams, or establishing cross-cutting patterns. Covers ADRs, diagram standards, API design, agent collaboration, and review gates.
basecoat-10-core-backend	instructions/basecoat-10-core-backend.instructions.md	src/**,lib/**,app/**,packages/**,api/**,server/**	Use when working on APIs, services, workers, integrations, or data access layers. Covers backend best practices for contracts, failure handling, and testability.
basecoat-10-core-bicep	instructions/basecoat-10-core-bicep.instructions.md	**/*.{bicep,bicepparam}	Use when creating or reviewing Azure Bicep files or parameter files. Covers symbolic names, parameters, secure values, and Bicep validation best practices.
basecoat-10-core-bootstrap-autodetect	instructions/basecoat-10-core-bootstrap-autodetect.instructions.md	**/bootstrap*.{ps1,sh},scripts/bootstrap*.{ps1,sh}	Use when writing or reviewing bootstrap scripts. Ensures scripts auto-detect values from context and run without interactive prompts.
basecoat-10-core-bootstrap-structure	instructions/basecoat-10-core-bootstrap-structure.instructions.md	**/bootstrap*.{ps1,sh}	Use when designing or reviewing bootstrap scripts. Covers decomposition, idempotency, documentation, and cross-platform requirements.
basecoat-10-core-capability-frontmatter	instructions/basecoat-10-core-capability-frontmatter.instructions.md	agents/**/*.agent.md,skills/**/SKILL.md	Use when authoring or reviewing agent and skill frontmatter with capability-first routing, justified model pinning, and safe fallback policy.
basecoat-10-core-config	instructions/basecoat-10-core-config.instructions.md	**/*.{json,yaml,yml,toml,env,ini,conf},**/config/**,**/.env*	Config file safety instructions. Apply before creating, modifying, or staging any configuration file. Ensures secrets stay out of source control.
basecoat-10-core-cpp	instructions/basecoat-10-core-cpp.instructions.md	**/*.{cpp,cc,cxx,c,h,hpp,hxx}	Use when AI generates or modifies C++ or native code. Covers memory safety, concurrency, undefined behavior, and mandatory validation with sanitizers.
basecoat-10-core-data-workload-testing	instructions/basecoat-10-core-data-workload-testing.instructions.md	**/*.{py,sql,yml}	Comprehensive test suite for data workloads: medallion patterns, data quality validation, and convention-driven testing for bronze/silver/gold layers.
basecoat-10-core-development	instructions/basecoat-10-core-development.instructions.md	**/*	Use when working with backend-dev, frontend-dev, middleware-dev, or data-tier agents. Covers shared code style, error handling, security, logging, testing, and agent collaboration expectations.
basecoat-10-core-documentation	instructions/basecoat-10-core-documentation.instructions.md	**/*	Use when a change affects setup, workflows, public contracts, operational behavior, or developer experience. Covers common documentation best practices.
basecoat-10-core-drift-monitor	instructions/basecoat-10-core-drift-monitor.instructions.md	**/*.tf,**/*.bicep,**/infra/**	Infrastructure-as-Code drift detection and remediation strategies
basecoat-10-core-electron	instructions/basecoat-10-core-electron.instructions.md	**/electron/**/*.{ts,tsx,js,jsx,cjs,mjs,json,yml,yaml},**/*electron*.{ts,tsx,js,jsx,cjs,mjs,json,yml,yaml,md}	Use when building secure Electron desktop applications. Covers process architecture, inter-process communication, content security policy, code signing, auto-updates, credential storage, and ASAR integrity. Reference skill at skills/electron-apps/SKILL.md for implementation patterns.
basecoat-10-core-enterprise-configuration	instructions/basecoat-10-core-enterprise-configuration.instructions.md	references/enterprise-configuration/**/*.md,instructions/basecoat-10-core-enterprise-configuration.instructions.md,.github/workflows/*.{yml,yaml}	Enterprise-level GitHub Copilot policy configuration, including usage metrics enablement, seat management, and security policies.
basecoat-10-core-error-kb	instructions/basecoat-10-core-error-kb.instructions.md	error-kb/**/*,**/*error*.{md,json,yml,yaml,ps1,sh,py,ts,js}	Use when building, extending, or consulting an error knowledge base so agents can classify failures, reuse proven fixes, and capture new patterns safely.
basecoat-10-core-escalation-criteria	instructions/basecoat-10-core-escalation-criteria.instructions.md	**/*	Use when deciding whether work should escalate for design review, approval, or compliance sign-off.
basecoat-10-core-fabric-notebooks	instructions/basecoat-10-core-fabric-notebooks.instructions.md	**/*.ipynb", "**/*notebook*	Deploy and manage Microsoft Fabric notebooks with CI/CD, lakehouse integration, governance, and production patterns.
basecoat-10-core-frontend	instructions/basecoat-10-core-frontend.instructions.md	**/src/**/*.{ts,tsx,js,jsx,css,scss,html},**/app/**/*.{ts,tsx,js,jsx,css,scss,html},**/components/**/*.{ts,tsx,js,jsx,css,scss,html},**/pages/**/*.{ts,tsx,js,jsx,css,scss,html}	Use when changing UI, client-side state, styling, forms, or interactions. Covers frontend best practices for accessibility, responsive behavior, and UX clarity.
basecoat-10-core-hrm-execution	instructions/basecoat-10-core-hrm-execution.instructions.md	**/*	HRM Phase 2 — Formal layer contracts, two-dimensional routing matrix, guidance signals, and agent decomposition scope rules for the BaseCoat execution hierarchy.
basecoat-10-core-intent-routing	instructions/basecoat-10-core-intent-routing.instructions.md	**/*	Intent prefix routing — interprets user-defined prefixes to determine urgency, timing, and which agents or skills to invoke. Applies to all conversations.
basecoat-10-core-j2ee-jakarta-ee	instructions/basecoat-10-core-j2ee-jakarta-ee.instructions.md	**/ejb-jar.xml,**/persistence.xml,**/*.war,**/web.xml,**/jboss*.xml	Use when migrating J2EE / Jakarta EE applications. Covers namespace migration, EJB modernization, Azure deployment targets, Strangler Fig decomposition, database migration, and auth modernization.
basecoat-10-core-mcp	instructions/basecoat-10-core-mcp.instructions.md	**/*.{md,json,yml,yaml,ts,js,py,ps1,sh}	Use when configuring, invoking, building, or reviewing MCP servers and MCP tool usage. Covers server development standards, tool definition conventions, transport protocols, trust boundaries, secrets handling, testing, and safe operation patterns.
basecoat-10-core-memory-index	instructions/basecoat-10-core-memory-index.instructions.md	**/*	L2 memory index. Loads at session start to prime fast pattern recall. Maps trigger contexts to known high-confidence patterns and subject tags for deeper retrieval. Keep under 500 tokens — index only, no full memories.
basecoat-10-core-model-routing	instructions/basecoat-10-core-model-routing.instructions.md	**/*	Use when dispatching sub-agents or choosing models for tasks. Provides cost-aware model routing to avoid over-spending on premium models for simple tasks.
basecoat-10-core-monolith	instructions/basecoat-10-core-monolith.instructions.md	src/**,lib/**,app/**,packages/**	Use when AI agents work on large monolith codebases with tightly coupled modules. Covers context scoping, dependency awareness, and safe decomposition strategies.
basecoat-10-core-mutation-testing	instructions/basecoat-10-core-mutation-testing.instructions.md	agents/basecoat-10-core-contract-testing.agent.md, agents/basecoat-90-quality-e2e-test-strategy.agent.md, instructions/basecoat-10-core-testing.instructions.md	>
basecoat-10-core-naming	instructions/basecoat-10-core-naming.instructions.md	**/*.{md,json,yml,yaml,ts,tsx,js,jsx,py,cs,java,go,tf,bicep,ps1,sh}	Use when defining repository, file, type, variable, test, infrastructure, or Azure resource names. Covers consistent naming conventions across code and platform assets.
basecoat-10-core-nextjs-react19	instructions/basecoat-10-core-nextjs-react19.instructions.md	**/*.tsx,**/*.ts,**/next.config.*	Next.js and React 19 frontend instruction covering Server Components, App Router, streaming, form actions, and modern patterns
basecoat-10-core-npm-workspaces	instructions/basecoat-10-core-npm-workspaces.instructions.md	**/package.json,**/turbo.json,**/pnpm-workspace.yaml	Setup and best practices for npm workspaces and monorepo management
basecoat-10-core-observability	instructions/basecoat-10-core-observability.instructions.md	**/*.{cs,ts,tsx,js,jsx,py,go,java,json,yml,yaml}	>
basecoat-10-core-output-style	instructions/basecoat-10-core-output-style.instructions.md	**/*	Use to keep agent responses concise by default while preserving clarity, accuracy, and full-fidelity code output.
basecoat-10-core-plan-first	instructions/basecoat-10-core-plan-first.instructions.md	**/*	Use when tasks require multiple steps, cross-file changes, or non-trivial design decisions. Enforces an explore-plan-implement-verify workflow so work stays scoped and intentional.
basecoat-10-core-process	instructions/basecoat-10-core-process.instructions.md	**/*	Use when planning sprints, triaging issues, managing pull requests, coordinating releases, or evaluating delivery health. Covers the end-to-end delivery lifecycle from intake through production release.
basecoat-10-core-public-guidance	instructions/basecoat-10-core-public-guidance.instructions.md	**/*	Use when converting internal roadmap or feedback into a separate public-safe guidance artifact.
basecoat-10-core-reliability	instructions/basecoat-10-core-reliability.instructions.md	**/*.{cs,ts,tsx,js,jsx,py,go,java,rb,ps1,json,yml,yaml}	Use when changing code paths where uptime, retries, background work, or dependency failures matter. Covers common reliability and operability best practices.
basecoat-10-core-rest-client-resilience	instructions/basecoat-10-core-rest-client-resilience.instructions.md	**/*.cs,**/*.ts,**/*.py,**/*.go	Use when building or reviewing HTTP client code that calls external APIs. Covers timeouts, retries, 429 handling, circuit breakers, and structured failure logging.
basecoat-10-core-runtime-debugging	instructions/basecoat-10-core-runtime-debugging.instructions.md	src/**,lib/**,app/**,packages/**,tests/**	Use when debugging requires runtime context such as crash dumps, logs, memory state, or production telemetry. Covers how to feed runtime data into AI-assisted debugging workflows.
basecoat-10-core-s4-safety-gates	instructions/basecoat-10-core-s4-safety-gates.instructions.md	.github/**/*	Use when defining S4 cutover safety gates, including shadow-mode validation, rollback testing, and on-call review.
basecoat-10-core-session-hygiene	instructions/basecoat-10-core-session-hygiene.instructions.md	**/*	Use when managing long-running Copilot sessions, switching tasks, or coordinating handoffs. Covers context hygiene, session rotation, and clean-state working practices.
basecoat-10-core-shearing-layers	instructions/basecoat-10-core-shearing-layers.instructions.md	**/*	Shearing Layers design framework — guides contributors and AI agents to reason about change velocity and coupling between BaseCoat layers.
basecoat-10-core-subagent-review	instructions/basecoat-10-core-subagent-review.instructions.md	**/*	Defines a two-stage review protocol for subagent task output. Stage 1 checks spec compliance, Stage 2 checks code quality. Applies when orchestrating multi-agent work.
basecoat-10-core-tdd-enforcement	instructions/basecoat-10-core-tdd-enforcement.instructions.md	src/**,lib/**,app/**,packages/**	Enforces RED-GREEN-REFACTOR test-driven development as a sequence gate for implementation work. Applies to feature code, bug fixes, and refactors in source directories.
basecoat-10-core-terraform	instructions/basecoat-10-core-terraform.instructions.md	**/*.{tf,tfvars}	Use when creating or reviewing Terraform for Azure or shared infrastructure. Covers provider pinning, state hygiene, modules, validation, and safe Terraform workflows.
basecoat-10-core-terraform-init	instructions/basecoat-10-core-terraform-init.instructions.md	**/*.tf,**/*.yml,**/*.ps1,**/*.sh	Use when running terraform init in bootstrap scripts or CI/CD pipelines. Ensures backend re-initialization doesn't block automation.
basecoat-10-core-testing	instructions/basecoat-10-core-testing.instructions.md	**/*	Use when adding, updating, or reviewing tests. Covers common testing best practices for regression protection, determinism, and change validation.
basecoat-10-core-tool-minimization	instructions/basecoat-10-core-tool-minimization.instructions.md	**/*	Use when configuring agent tool access or planning task execution. Enforces selective tool enablement, lower context noise, and disciplined MCP server usage.
basecoat-10-core-trm-reflexion	instructions/basecoat-10-core-trm-reflexion.instructions.md	**/*	TRM (Tiny Recursive Model) Reflexion loop for intent classification and turn budget estimation. Apply whenever classifying task intent or tracking progress against a turn budget.
basecoat-10-core-ux	instructions/basecoat-10-core-ux.instructions.md	**/*.{tsx,jsx,html,css,scss,vue,svelte,astro},docs/ux/**,docs/design-system.md	Use when working on user experience, interface design, accessibility, component specifications, or user journey mapping. Covers design system reference, WCAG compliance, naming conventions, handoff format, and journey standards.
basecoat-10-core-verification	instructions/basecoat-10-core-verification.instructions.md	**/*	Use when planning, implementing, or reviewing changes. Requires explicit success criteria before coding and completed verification with evidence before declaring work done.
basecoat-20-lang-django	instructions/basecoat-20-lang-django.instructions.md	**/manage.py,**/wsgi.py,**/asgi.py,**/settings.py,**/urls.py	Use when working on Django applications targeting Azure. Covers Azure deployment targets, production configuration, PostgreSQL, Entra ID OIDC auth, Redis sessions, and CI/CD.
basecoat-20-lang-dotnet-dependency-analysis	instructions/basecoat-20-lang-dotnet-dependency-analysis.instructions.md	**/*.{sln,csproj,props,targets,json}	.NET dependency compatibility and remediation analysis guidance.
basecoat-20-lang-dotnet-test-strategy	instructions/basecoat-20-lang-dotnet-test-strategy.instructions.md	**/*.{sln,csproj,props,targets,cs,yml,yaml}	.NET modernization test strategy and regression-gate guidance.
basecoat-20-lang-dotnet-upgrade-planning	instructions/basecoat-20-lang-dotnet-upgrade-planning.instructions.md	**/*.{sln,csproj,props,targets,cs,json,yml,yaml}	.NET upgrade planning checklist and phased execution guidance.
basecoat-20-lang-governance	instructions/basecoat-20-lang-governance.instructions.md	**/*	CRITICAL — Read this first. Governance rules for all AI agents working in this repository. Covers issue-first mandate, secret policy, PR-only workflow, branch naming, when to stop vs proceed, and token/model awareness stub.
basecoat-20-lang-java-spring-boot	instructions/basecoat-20-lang-java-spring-boot.instructions.md	**/*.java,**/pom.xml,**/build.gradle,**/application.yml,**/application.properties	Conventions for Java Spring Boot projects targeting Azure: deployment targets, containerization, database migration, auth modernization, and CI/CD patterns.
basecoat-20-lang-python	instructions/basecoat-20-lang-python.instructions.md	**/*.py	Conventions for Python-centric projects, including data science and ML pipelines with pandas, scikit-learn, DuckDB, and Jupyter notebooks.
basecoat-20-lang-ruby-on-rails	instructions/basecoat-20-lang-ruby-on-rails.instructions.md	**/Gemfile,**/config.ru,**/.ruby-version,**/Rakefile,**/config/routes.rb	Conventions for Ruby on Rails projects targeting Azure: deployment targets, containerization, database migration, auth modernization, and CI/CD patterns.
basecoat-30-ai-ai-verification	instructions/basecoat-30-ai-ai-verification.instructions.md	**/*	Use when reviewing or accepting AI-generated code. Provides a risk-tiered verification protocol to reduce trust overhead while catching real issues.
basecoat-30-ai-tailwind-v4	instructions/basecoat-30-ai-tailwind-v4.instructions.md	**/*.css,**/*.tsx,**/*.html	Tailwind CSS v4 patterns, CSS-first configuration, and migration guidance
basecoat-40-azure-azure	instructions/basecoat-40-azure-azure.instructions.md	**/*.{bicep,bicepparam,tf,tfvars,ps1,json,yml,yaml,ts,js,py,cs}	Use when working on Azure services, Azure SDK integrations, Azure deployment configuration, or cloud architecture for Azure. Covers secure Azure defaults, authentication, and service usage patterns.
basecoat-40-azure-azure-app-configuration	instructions/basecoat-40-azure-azure-app-configuration.instructions.md	**/*.{bicep,bicepparam,tf,tfvars,ps1,sh,json,yml,yaml,cs,ts,js,py}	Use when working with Azure App Configuration — centralizing feature flags, application settings, and dynamic configuration for Azure-hosted applications.
basecoat-40-azure-azure-service-connector	instructions/basecoat-40-azure-azure-service-connector.instructions.md	**/*.{bicep,bicepparam,tf,tfvars,ps1,sh,json,yml,yaml,cs,ts,js,py}	Use when working with Azure Service Connector — connecting App Service, Container Apps, AKS, or Azure Functions to backing services (databases, storage, cache, messaging) using passwordless authentication.
basecoat-50-security-bootstrap-github-secrets	instructions/basecoat-50-security-bootstrap-github-secrets.instructions.md	**/bootstrap*github*.{ps1,sh},**/bootstrap*secret*.{ps1,sh},**/bootstrap*vars*.{ps1,sh},scripts/*github*.{ps1,sh},scripts/*secret*.{ps1,sh},scripts/*vars*.{ps1,sh}	Use when writing bootstrap scripts that provision identity or infrastructure for GitHub Actions. Ensures CI/CD secrets and variables are pushed automatically.
basecoat-50-security-copilot-github-token-bootstrap	instructions/basecoat-50-security-copilot-github-token-bootstrap.instructions.md	**/scripts/bootstrap-copilot-github-token.ps1,docs/operations/GITHUB_SECRETS.md	Use when configuring COPILOT_GITHUB_TOKEN for gh-aw workflows. Enforces repo-level secret setup, least-privilege token guidance, and non-echo handling for PAT input.
basecoat-50-security-entra-oidc-user-auth	instructions/basecoat-50-security-entra-oidc-user-auth.instructions.md	**/auth/**,**/identity/**,**/*.bicep,**/iac/**,**/.github/workflows/**	Use when implementing human user authentication via browser — Authorization Code Flow with PKCE, confidential client flows, MSAL token caching, and Entra ID app registration. Complements bac-authentication.instructions.md which covers service-to-service managed identity.
basecoat-50-security-rbac-authentication	instructions/basecoat-50-security-rbac-authentication.instructions.md	**/*.tf,**/*.bicep,**/*.cs,**/*.ts,**/*.py	Use when provisioning or reviewing Azure resources. Enforces RBAC-only authentication — no shared keys, SAS tokens, access policies, or connection string auth.
basecoat-50-security-secrets-management	instructions/basecoat-50-security-secrets-management.instructions.md	agents/basecoat-50-security-secrets-manager.agent.md, agents/basecoat-10-core-devops-engineer.agent.md, agents/basecoat-60-workflow-infrastructure-deploy.agent.md	>
basecoat-50-security-security	instructions/basecoat-50-security-security.instructions.md	**/*	Use when working on authentication, authorization, secrets, input handling, or any change with security implications. Covers common secure coding best practices.
basecoat-50-security-security-monitoring	instructions/basecoat-50-security-security-monitoring.instructions.md	agents/basecoat-50-security-security-monitor.agent.md, agents/basecoat-50-security-config-auditor.agent.md, agents/basecoat-60-workflow-incident-responder.agent.md	>
basecoat-50-security-token-economics	instructions/basecoat-50-security-token-economics.instructions.md	**/*	Use when selecting models, escalating reasoning cost, or loading context. Enforces cost-aware routing and token budget discipline for all agent work.
basecoat-60-workflow-ci-firewall	instructions/basecoat-60-workflow-ci-firewall.instructions.md	**/*.yml,**/*.yaml	Use when writing GitHub Actions workflows that access firewalled Azure resources (Storage, Key Vault, SQL, Cosmos). Covers the single-job runner IP pattern with guaranteed cleanup.
basecoat-60-workflow-factory-orchestration	instructions/basecoat-60-workflow-factory-orchestration.instructions.md	.github/**/*	Use when editing factory orchestration workflows, state files, escalation paths, or Workcell triggers.
basecoat-60-workflow-high-stakes-workflow	instructions/basecoat-60-workflow-high-stakes-workflow.instructions.md	**/*	Enforces a mandatory sequential workflow for high-stakes changes. Prevents skipping phases when work involves architecture, public APIs, multi-agent dispatch, or new features with broad impact.
basecoat-60-workflow-multi-repo-orchestration	instructions/basecoat-60-workflow-multi-repo-orchestration.instructions.md	.github/workflows/*.yml	Multi-repo orchestration guidance for hub-and-spoke CI/CD patterns using workflow_dispatch.
basecoat-60-workflow-workflow-file-integrity	instructions/basecoat-60-workflow-workflow-file-integrity.instructions.md	.github/workflows/**/*.{yml,yaml},scripts/**/*.{ps1,sh,py}	Guard against silent GitHub Actions workflow file corruption and enforce checksum validation when programmatically modifying workflow YAML.
basecoat-60-workflow-workflow-integrity	instructions/basecoat-60-workflow-workflow-integrity.instructions.md	.github/workflows/**	Prevent common GitHub Actions workflow security vulnerabilities including script injection, credential embedding, and unpinned actions.
basecoat-80-data-data-science	instructions/basecoat-80-data-data-science.instructions.md	**/*.{py,ipynb}	Conventions for data science, ML, and notebook-driven projects using Jupyter, pandas, scikit-learn, DuckDB, and the medallion lakehouse architecture.
basecoat-90-quality-quality	instructions/basecoat-90-quality-quality.instructions.md	**/*	Use when reviewing PRs, evaluating security posture, measuring performance, or enforcing coverage thresholds. Covers quality gates that every change must pass and how review agents collaborate.
ci-firewall	instructions/ci-firewall.instructions.md	**/*.yml,**/*.yaml	BaseCoat compatibility alias for CI/CD runner firewall management. Preserves the legacy filename while the prefixed BaseCoat instruction is the canonical source.
documentation	instructions/documentation.instructions.md	**/*	BaseCoat compatibility alias for documentation guidance. Preserves the legacy filename while the prefixed BaseCoat instruction is the canonical source.
governance	instructions/governance.instructions.md	**/*	BaseCoat compatibility alias for governance rules. Preserves the legacy filename while the prefixed BaseCoat instruction is the canonical source.
intent-routing	instructions/intent-routing.instructions.md	**/*	BaseCoat compatibility alias for intent prefix routing. Preserves the legacy filename while the prefixed BaseCoat instruction is the canonical source.
observability	instructions/observability.instructions.md	**/*	BaseCoat compatibility alias for observability guidance. Preserves the legacy filename while the prefixed BaseCoat instruction is the canonical source.
plan-first	instructions/plan-first.instructions.md	**/*	BaseCoat compatibility alias for the plan-first workflow. Preserves the legacy filename while the prefixed BaseCoat instruction is the canonical source.
rbac-authentication	instructions/rbac-authentication.instructions.md	**/*.tf,**/*.bicep,**/*.cs,**/*.ts,**/*.py	BaseCoat compatibility alias for RBAC-only Azure authentication. Preserves the legacy filename while the prefixed BaseCoat instruction is the canonical source.
security	instructions/security.instructions.md	**/*	BaseCoat compatibility alias for security guidance. Preserves the legacy filename while the prefixed BaseCoat instruction is the canonical source.
ux	instructions/ux.instructions.md	**/*	BaseCoat compatibility alias for UX guidance. Preserves the legacy filename while the prefixed BaseCoat instruction is the canonical source.

Prompts

Prompt	File	Description
portal-audit-risk-analysis	portal/prompts/portal-audit-risk-analysis.prompt.md	AI-powered security audit finding risk assessment with severity scoring and compliance impact analysis
portal-compliance-mapping	portal/prompts/portal-compliance-mapping.prompt.md	AI-powered compliance standards mapping with requirement verification and audit evidence guidance
portal-plain-language	portal/prompts/portal-plain-language.prompt.md	AI-powered compliance finding explanation in plain language for non-technical compliance officers and executives
portal-remediation-planning	portal/prompts/portal-remediation-planning.prompt.md	AI-powered compliance remediation planning with phased execution steps and resource estimation
portal-threat-analysis	portal/prompts/portal-threat-analysis.prompt.md	AI-powered security threat analysis with OWASP mapping, attack vector assessment, and control recommendations
architect	prompts/architect.prompt.md	Use when you want an implementation plan before editing code. Helps break down a feature or system change into options, tradeoffs, and execution steps.
bugfix	prompts/bugfix.prompt.md	Use when investigating a bug, regression, or production failure. Focuses on root-cause analysis, a minimal safe fix, and validation.
code-review	prompts/code-review.prompt.md	Use when you want a risk-focused code review of a diff, branch, or set of files. Returns findings first, then open questions, then a short summary.
integrate	prompts/integrate.prompt.md	Integrate BaseCoat into a repository and run a baseline audit. Invoke with a GitHub repo URL or run from inside the target repo. Works in GitHub Copilot CLI, VS Code Copilot Chat, and any editor with Copilot Chat support.
plan-sharedStandardsRepo	prompts/plan-sharedStandardsRepo.prompt.md	Use when planning a shared standards repository with auto-sync capabilities for GitHub Copilot customizations across teams.

Related References

• inventory.md
• asset-catalog.md
• TOKEN_CONTEXT_INVENTORY.md