17,691 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
Skill Claude CodeCodex
Use when reviewing a pull request, before posting any feedback. Runs fully automated in GitHub Actions. Detects intent, identifies specs via Linear, dispatches expert agents, classifies findings by severity, and posts inline comments on the exact lines that matter.
Skill Claude CodeCodex
Surface architectural friction and propose deepening candidates after ratifying or bootstrapping a load-bearing project Glossary.md. Insists on a consistent glossary as a precondition for any review.
Skill Claude CodeCodex
Use when a pull request has review feedback waiting and you want to act on all of it — CodeRabbit, GitHub Copilot, Gemini Code Assist, and any other review bot, plus human reviewers. Collects inline review threads, review summary bodies, and pull request comments, extracts the CodeRabbit findings that never reach the…
Skill Claude CodeCodex
Run visible multi-agent spec reviews in Herdr through interactive agent CLIs such as Claude, Codex, Copilot/GLM, or Grok/Composer. Supports two modes — a spec review (the design, before implementation) and an implementation review (the implemented diff vs the spec, after the calling model has built it). Ask for…
Skill Claude CodeCodex
Review backend code that integrates with external/third-party APIs (payment providers, banks, KYC, card networks, crypto exchanges, SMS/OTP, any outbound HTTP/gRPC to a system you do not own). Checks planning of failure modes, idempotency, timeout and retry strategy, response code classification, duplicate-transaction…
Skill Claude Code
Fetch PR review comments from GitHub, investigate each one against the actual codebase, and fix real issues. Use after a PR review to triage and act on reviewer feedback, or when asked to "check PR comments", "handle review feedback", or "investigate PR".
Plugin Claude Code
Bundles 25 skills, 25 commands, 9 agents, 2 hooks · 4,323 tokens together
optimiziramsi's Claude Code toolkit as ONE plugin, organized topic-first — one folder per concern (git, commit, reporting, session, review, repo, instructions, flow, patterns, worktree, setup), each owning its own skills/commands/agents/hooks. Opinionated concerns carry env kill-switches; guards self-gate on project…
Skill Claude CodeCodex
A full-project bug audit that has two AI reviewers inspect source files independently and compare their findings.
Skill Claude Code needs its repo
Performs a fix-first code review with conditional specialists and a GO/NO-GO verdict.
Skill Claude CodeCodex
Triage and fix review findings that already exist on a GitHub PR, then reply and resolve the threads. Use on a CodeRabbit review URL, a PR whose review comments still need working through, or a local /review-pr findings file. When the PR has no findings yet, /review-pr produces them first.
Skill Claude CodeCodex
Security auditing skill for web applications and codebases. Scans for OWASP Top 10, dependency vulnerabilities, secrets exposure, XSS/CSRF/injection flaws, auth weaknesses, and misconfigurations. Use when task involves security scan, vulnerability assessment, pen test review, threat modeling, or hardening a codebase.
MCKRUZ/intent-driven-development
Agent Claude Code
Reviews user-facing Angular changes for UX quality: every state exists (loading, empty, error, success), accessibility basics hold, components follow the codebase's existing patterns, and the flow works end-to-end. Angular-aware — also catches the framework's own failure modes. Use PROACTIVELY when a change adds or…
Skill Claude Code
Run a cold Gate-1 spec review against a GitHub work-item issue. Use when a GH issue body needs reviewing AS A SPEC (not as code, not as a build request) — "spec review", "Gate 1", "review the issue as a spec", "/spec-review ". Spawns a fresh subagent that reads only the published issue, reports findings, and never…
Agent Claude Code
Level 2 orchestrator. Coordinates comprehensive code reviews across all dimensions by routing PR changes to appropriate specialist reviewers. Select when PR analysis and specialist coordination required.
Skill Claude CodeCodex
Deep review of all changes on the current branch using scaled finder agents with deduplication, falsification, and intent verification.
Skill Claude CodeCodex
A self-review checklist for software plans and code changes, with fourteen review areas and a final acceptance check.
sungeunkim0127/claude-code-bootcamp
Skill Claude CodeCodex
Performs comprehensive code review with security, performance, and quality checks.
Skill Claude CodeCodex
Teach AI to review like your team: custom review checklists, tone calibration, org-specific patterns, and AI-assisted code review workflows.
Command Claude Code
Command "code-review" from r0r1/claude_code_config, covering review github pr with linear issue specification, arguments provided, prerequisites check, step 1: extract github repository and pr information and step 2: fetch linear issue details.
Agent Claude Code
Senior VBA code review specialist. Use after writing or modifying VBA to review for security, quality, performance, and best practices before committing or releasing.
Agent Claude Code
Enforces architectural integrity by validating layering, module boundaries, domain rules, and separation of concerns across the codebase.
Agent Claude Code
Research code reviewer. Use when reviewing PyTorch/ML code to flag over-engineering and encourage simple, readable code.
Skill Claude CodeCodex
Assess an existing codebase's coupling and cohesion — module cohesion and LCOM, codebase-wide coupling metrics and zones, or whether a single dependency is balanced (Khononov).
Cursor rule Cursor
A pre-commit and pre-pull-request review for OneKey QA changes. It scans staged, unstaged, and untracked files for security leaks, test-case and rule quality, and script problems, then writes a detailed report.
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: