Hook Claude Code
Runs before the agent uses a tool for Edit, Write, MultiEdit, Read, Glob, Grep, Write and Bash tool calls, executing require-migration-ticket.sh, require-active-ticket.sh, detect-role-trigger.sh, suggest-mcp-search.sh, warn-review-marker-write.sh, block-git-add-all.sh, block-main-push.sh, validate-branch-name.sh…
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, executing detect-role-trigger.sh and detect-skill-intent.sh via bash (2 commands). From me2resh/apexyard.
Hook Claude Code
Runs after a tool call finishes for Bash, Write, Edit and MultiEdit tool calls, executing auto-code-review.sh, warn-stale-review-markers.sh, suggest-mcp-reindex-after-clone.sh, suggest-mcp-reindex-after-pull.sh and maintain-docs-index.sh via bash (5 commands). From me2resh/apexyard.
Settings file Claude Code
Agent settings declaring 4 hook events (SessionStart, PreToolUse, UserPromptSubmit, PostToolUse).
Skill Claude CodeCodex
WCAG 2.2 AA audit — perceivable, operable, understandable, robust criteria. Deep-dive for /launch-check accessibility.
Skill Claude CodeCodex
Browse / search / show / stats AgDRs across the portfolio — recalls "have we decided this before?".
Skill Claude CodeCodex
Analytics audit — SDK config, event naming, funnel completeness, dashboards. Deep-dive for /launch-check analytics.
Skill Claude CodeCodex
Record per-PR architecture-review approval for design-artifact PRs (required by the architecture gate). ONLY on an explicit per-PR architect "approved".
Skill Claude CodeCodex
Record per-PR design-review approval (UI merge gate). ONLY on an explicit per-PR designer "approved".
Skill Claude CodeCodex
Record per-PR CEO approval and merge in one turn. ONLY on an explicit per-PR "approved" — never on umbrella "go".
Skill Claude CodeCodex
Audit dependencies for vulnerabilities, outdated packages, and license compliance.
Skill Claude CodeCodex
Create a structured bug ticket (Given/When/Then scenario, repro steps, severity).
Skill Claude CodeCodex
Generate C4 L1 (Context) + L2 (Container) Mermaid diagrams from a project's codebase. Structurizr DSL escape hatch (--dsl) for L3+ component precision.
Skill Claude CodeCodex
Invoke The Contrarian (Naqid) to steelman-then-challenge an idea, feature, decision, or plan — surfaces assumptions, failure modes, and alternatives. Advisory only; never blocks a gate.
Skill Claude CodeCodex
Review a PR for quality, security, and standards compliance. Invokes the Code Reviewer agent (Rex).
Skill Claude CodeCodex
Turn a review comment that caught a Rex-miss into a draft handbook entry — Y/N gate, source-PR footer, bucket-routed.
Skill Claude CodeCodex
GDPR + ePrivacy audit — consent, privacy policy, data handling, right-to-deletion, DPAs. Deep-dive for /launch-check compliance.
Skill Claude CodeCodex
Hypothesis-driven debugging — architecture-first reading + evidence-before-fix. For bugs that resisted naïve fix attempts.
Skill Claude CodeCodex
Make a technical decision with structured reasoning and create an Agent Decision Record (AgDR).
Skill Claude CodeCodex
Review a technical design / migration AgDR / feature spec for architectural soundness BEFORE the Build phase. Invokes the Solution Architect agent (Tariq) — the non-code analog of /code-review.
Skill Claude CodeCodex
Sync a local component library to a claude.ai/design design-system project incrementally — one component at a time, never a wholesale replace. Drives the DesignSync tool.
Skill Claude CodeCodex
DFD with trust boundaries + data classifications (Mermaid + optional Threat Dragon JSON). Source-of-truth for /threat-model.
Skill Claude CodeCodex
Diataxis docs audit — tutorials, how-to, reference, explanation; checks README, API docs, deployment guides, changelog, staleness.
Skill Claude CodeCodex
Score a review agent (Rex/Hakim/Tariq) against a labeled PR corpus — ground-truth defect-set overlap, never a prose rubric. Headline metric is approve-precision.