Agent Claude Code
Use for systematic investigation of bugs, test failures, or runtime errors. Reproduces first, then forms 2-3 ranked hypotheses with evidence, investigates code paths and git history, and proposes the minimal fix. Never guesses; never shotgun-debugs. Returns a single report — does not modify code.
Command Claude Code
Detect project type (Node/Python/Rust/Go/mixed) and propose CLAUDE.md + settings.json additions for lint, typecheck, and test commands. Pure inspection — applies nothing without explicit user approval.
Command Claude Code
Generate a conventional commit message for staged changes (feat/fix/refactor/...) and run git commit. Refuses if sensitive files are staged.
Command Claude Code
Structured development cycle — Research → Feasibility → Plan → Implement → Verify with persistent memory and feedback replay.
Command Claude Code
Fast session handover — capture current state and write a resume command for the next session. Use when context is filling up or you need to switch tasks.
Command Claude Code
Persist a single insight, decision, or constraint to long-term memory with auto-classified category and tags.
Command Claude Code
Structured codebase orientation — understand an unfamiliar project before making changes. Maps architecture, conventions, entry points, and gotchas.
Command Claude Code
Project-local release pipeline — bump version, regenerate CHANGELOG from commits since last tag, update README docs for new features (with concrete examples + argument explanations), commit + tag + push, open a PR if on a non-main branch, then hand off a manual npm publish (no token configured yet).
Command Claude Code
Full-text search persistent memory (BM25) and present results grouped by category — decisions, constraints, learnings, tasks.
Command Claude Code
Review the working diff (unstaged + staged) against a correctness, regressions, security, performance, and style checklist.
Command Claude Code
Capture testable acceptance criteria for a feature before implementation. BA hat — ambiguities surfaced, scope bounded, success defined.
Command Claude Code
Generate a test scaffold for a file or function following the testing skill protocol — boundary, happy path, edge cases, error cases. Does not run; produces the file.
Command Claude Code
End-of-session protocol — capture decisions, constraints, learnings, and next-session task; create a session snapshot before context is lost.
Skill Claude CodeCodex
Use when designing or reviewing a public API surface — REST/GraphQL/gRPC, versioning, idempotency, error contracts, pagination, auth boundary. Helps choose between transport styles and avoid breaking-change footguns.
Skill Claude CodeCodex
Use when making structural decisions, choosing service boundaries, evaluating coupling/cohesion, or deciding whether to add a new component. Helps reason about dependency direction (domain ← application ← infrastructure) and avoid distributed monoliths or premature abstractions.
Skill Claude CodeCodex
Use when designing a database schema from scratch or evaluating storage trade-offs — entity modeling, normalization, indexing strategy, SQL vs NoSQL choice, read/write patterns, schema evolution plan. Complements the migration skill (which handles changing existing schemas).
Skill Claude CodeCodex
Use when investigating a bug, regression, or unexpected behavior. Enforces reproduce → isolate → hypothesize → verify → fix → prevent — fixing root causes rather than symptoms, and adding a regression test before closing.
Skill Claude CodeCodex
Use when changing a database schema or backfilling data in production — adding/removing columns, changing types, dropping tables, reindexing. Enforces lock-impact analysis, dual-write transitions, and rollback plans before any DDL runs.
Skill Claude CodeCodex
Use when investigating slowness, planning optimizations, or reviewing a hot path. Enforces "measure first" — profile before optimizing, fix algorithm before I/O, never add caches before fixing the underlying query. Covers DB indexing, N+1, and request-path I/O hygiene.
Skill Claude CodeCodex
Use when designing or reviewing a system for security properties — threat modeling, trust boundaries, auth design, input validation strategy, secret management, dependency risk. Focuses on design-time security decisions, not just code-level vulnerabilities (use Claude Code's built-in security-review skill for code…
Skill Claude CodeCodex
Use when writing or reviewing tests — choosing what to test, structuring test suites, deciding on real deps vs mocks, or after fixing a bug (regression test). Emphasizes testing behavior over implementation and progressing boundary → happy path → edge cases → errors.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: