Agent Claude Code
Safe cross-file refactoring agent. Renames, symbol extraction, module restructuring, pattern-based code transformation. Uses ast-grep for structural search/replace and impact analysis. Dry-run first, verify no breakage. Hard refuses new features or behavioral changes — refactor only.
Agent Claude Code
Surgical 1-2 file edit. Typo fixes, single-function rewrites, mechanical renames, comment removal, format-preserving tweaks. Hard refuses 3+ file scope. Returns a terse diff receipt. Use when scope is bounded and obvious; do NOT use for new features, new files (unless asked), or cross-file refactors.
Agent Claude Code
Minimal fix agent. Reads error output, makes 1-file surgical fix. No discovery, no exploration, no context beyond the error itself. Use when test fails, build breaks, or lint error needs fixing. Hard refuses multi-file changes, new features, or speculative refactors. Faster than graphcrew-builder for pure fix work …
Agent Claude Code
Read-only code locator. Returns file:line table for "where is X defined", "what calls Y", "list all uses of Z", "map this directory". Output is compressed so the main thread eats 60% fewer tokens than vanilla Explore. Refuses to suggest fixes.
Agent Claude Code
Diff/branch/file reviewer. One line per finding, severity-tagged, no praise, no scope creep. Output format path:line: : . . Use for "review this PR", "review my diff", "audit this file". Skips formatting nits unless they change meaning.
Skill Claude CodeCodex
Use when the user wants to create AI video generation prompts for a brand, product, website, or topic. Includes interactive Q&A flow to gather requirements then outputs a single unified prompt (one paste) for tools like OmniFlash, Runway, Pika, Kling, Sora. Do NOT use for HyperFrames/Remotion video creation workflows.
Skill Claude CodeCodex
Use this skill when freezing the interface between a backend and its clients before parallel work starts, or when changing an endpoint other code already calls - request/response shapes, status codes, error envelope, pagination, filtering, idempotency, versioning, and the breaking-change rules. Covers writing the…
Skill Claude CodeCodex
Use this skill when building or reviewing a server-side endpoint, route handler, server action, webhook, cron job, or background worker in any language. Covers per-route authorization and IDOR, input validation at the trust boundary, rate limiting, SSRF, file uploads, JWT and session handling, tenant isolation, and…
Skill Claude CodeCodex
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. Continuation mode: infer requirements, state assumptions, propose design in one message — no Q&A loop.
Skill Claude CodeCodex
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn cavecrew-investigator (locate code), cavecrew-builder (1-2 file edit), or cavecrew-reviewer (diff review) instead of doing the work inline or using vanilla Explore. Subagent output is caveman-compressed so the tool-result…
Skill Claude CodeCodex
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit.…
Skill Claude CodeCodex
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or…
Skill Claude CodeCodex
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
Skill Claude CodeCodex
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts token usage 75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or…
Skill Claude CodeCodex
Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.
Skill Claude CodeCodex
Database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate).
Skill Claude CodeCodex
Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.
Skill Claude CodeCodex
Use this skill before adding a dependency, when an audit or Dependabot alert fires, or when a lockfile changes in a review - triaging CVEs by real reachability, spotting typosquats and install scripts, pinning and lockfile discipline, and license checks. Covers deciding what actually needs fixing instead of chasing…
Skill Claude CodeCodex needs its repo
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.
Skill Codex needs its repo
Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.
Skill Claude CodeCodex
Patterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit breakers, and user-facing error messages.
Skill Claude CodeCodex
Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.
Skill Claude CodeCodex
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
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: