Agent Claude Code
Use after finishing a change in this repo to check it against CODINGGUIDELINES.md's rigor tiers, the testing mandate, and COMPLETIONCHECKLIST.md before calling the work done — flags gaps, does not fix them.
Hook Claude Code
Runs when a session starts, executing agent-lock.sh. From andr-ca/agentharness.
Hook Claude Code
Runs before the agent uses a tool for Bash, Write and Edit tool calls, executing claude-push-lock-guard.sh, claude-pr-merge-guard.sh and claude-outside-repo-write-guard.sh via bash (3 commands). From andr-ca/agentharness.
Hook Claude Code
Runs when the agent finishes a response, executing check-completion.sh via bash with --quiet. From andr-ca/agentharness.
Settings file Claude Code
Agent settings declaring 3 hook events (SessionStart, PreToolUse, Stop).
Skill Claude CodeCodex
Use when building or reviewing web UIs for accessibility — WCAG 2.2 Level AA compliance, semantic HTML over ARIA, keyboard navigation, color contrast, screen reader patterns, and testing approach.
Skill Claude CodeCodex
Use when building multi-turn agents, tool-calling systems, agent orchestration, or autonomous workflows — covers loops, tool calling, branching, reflection patterns.
Skill Claude CodeCodex
Use when designing, reviewing, or evolving a REST or GraphQL API — resource naming, HTTP status codes, versioning strategy, error response shapes, pagination, and authentication patterns.
Skill Claude CodeCodex
Use when asked to check whether review/audit recommendations were actually implemented, whether gaps were closed, or to re-score the repo — verifies claims against repo state instead of trusting status reports.
Skill Claude CodeCodex
Use before implementing big work — new systems, pipelines, daemons, or anything stateful/concurrent — where a bug would be expensive to find after code exists. Requires a written implementation plan to pass multi-round adversarial review by two independent LLM reviewers before any code is written. Not for scoped bug…
Skill Claude CodeCodex
Use when creating a branch, naming it, deciding whether to use a worktree, or handling secrets accidentally committed to history — branch naming convention, trunk protection, and secrets-removal procedure.
Skill Claude CodeCodex
Use when business logic is entangled with frameworks or databases. Covers hexagonal architecture (ports and adapters), layer diagram, dependency direction rules, and violation symptoms.
Skill Claude CodeCodex
Use when reviewing REST or HTTP API endpoints, controllers, or route handlers. Covers HTTP status codes, idempotency, versioning, auth, pagination, error shapes, and rate limiting. Load instead of the general code-review skill for API-focused reviews.
Skill Claude CodeCodex
Use when reviewing code that touches the database or persistence layer. Covers index strategy, query count, N+1, transaction scope, migration safety, and connection pooling. Load instead of the general code-review skill for DB-focused reviews.
Skill Claude CodeCodex
Use when reviewing frontend, UI, or component code. Covers accessibility (WCAG AA), state management, bundle size, keyboard navigation, hydration, and rendering performance. Load instead of the general code-review skill for UI-focused reviews.
Skill Claude CodeCodex
Use when reviewing a diff, pull request, or code change — systematic checklist for correctness, clarity, security, testability, and adherence to the project's conventions. Covers what to look for, how to give actionable feedback, and when to approve vs. request changes.
Skill Claude CodeCodex
Use when creating a git commit — atomic commits, message format, what never to commit, and the agent workflow-completion requirement (run completion gate; stage or publish per publish authority).
Skill Claude CodeCodex
Use when designing a database schema, writing migrations, reviewing SQL queries, or choosing between relational and document models — covers naming, index strategy, migration safety, N+1 prevention, and transaction boundaries.
Skill Claude CodeCodex
Use when adding dependencies, reviewing a project's dependency tree, or checking for known vulnerabilities and ownership risk — covers pip-audit, npm audit, govulncheck, lock file hygiene, update policy, and trust assessment.
Skill Claude CodeCodex
Use when writing or reviewing code with object graphs, service dependencies, or testability concerns. Covers constructor injection, DI containers, lifetimes, and anti-patterns (service locator, ambient context, over-injection).
Skill Claude CodeCodex
Use when recognizing a recurring design problem. Covers GoF patterns: Factory, Builder, Strategy, Observer, Command, Template Method, Decorator, Repository, Facade — when to apply each and when not to.
Skill Claude CodeCodex
Use when writing a Dockerfile, docker-compose file, or CI containerization config — multi-stage builds, layer caching, security (non-root user, minimal base images, no secrets in layers), and health checks.
Skill Claude CodeCodex
Use when building error recovery, handling exceptions, designing error flows, or implementing logging for errors — covers retry, circuit-breaker, error wrapping, structured logging.
Skill Claude CodeCodex
Use before creating any new file or directory in an established project — covers guarded root paths, docs/, src/, conf/, the allowed-additions escape hatch, and how to ask for permission. Load this skill at the start of every session in a project that has .agentharness-guarded-paths.json.