25,664 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
Review Benchflow or SkillsBench task-run trajectories and integration-test Benchflow code changes. Use this skill whenever the user asks to audit traj health, failed or timed-out runs, healthy pass/fail/timeout status, no-skill leakage, skill loading, reward hacking, verifier isolation, metadata completeness, token…
Skill Claude CodeCodex
AI Pair Collaboration Skill. Coordinate multiple AI models to work together: one creates (Author/Developer), two others review (Codex + Gemini). Works for code, articles, video scripts, and any creative task. Trigger: /ai-pair, ai pair, dev-team, content-team, team-stop.
fullstack-development/front-end-best-practices
Agent
Use when reviewing React+TypeScript code for compliance with frontend standards. Reviews modified files from git diff or a specific file/folder. Reports violations with file:line references and suggests fixes. Invoke as: @frontend-reviewer (reviews git diff) or @frontend-reviewer (reviews specific path).
Skill Claude CodeCodex
Identify security vulnerabilities and suggest secure coding practices.
Plugin Claude Code
Bundles 4 skills · 207 tokens together
Security code review skill based on Project CodeGuard's comprehensive security rules. Helps AI coding agents write secure code and prevent common vulnerabilities.
safaiyeh/app-store-review-skill
Plugin Claude Code
Bundles 1 skill · 76 tokens together
Evaluates code against Apple's App Store Review Guidelines for iOS, macOS, tvOS, watchOS, and visionOS apps.
Skill Claude CodeCodex
Evaluate Agent Skill design quality with an opinionated, practice-derived rubric informed by public specifications and examples. Use when reviewing, auditing, comparing, or improving SKILL.md files and skill packages. Produces evidence-backed findings, optional multi-dimensional scoring, and prioritized changes; treat…
apollographql/apollo-mcp-server
Skill Claude CodeCodex
Review a GitHub pull request for a Rust codebase. Focuses on security, performance, test coverage, and Rust idioms. Runs in GitHub Actions and posts comments directly to the PR.
Command Claude Code
Command "jprompt_ultra_diff_review" from disler/aider-mcp-server, covering ultra diff review, task 1: create diff.txt, code review, diff and task 2: git diff and append.
Instructions file
Claude Code instructions for Get-Concord-AI/concord-mcp, covering concord mcp — engineering guide, what this project is, coding rules (non-negotiable), the "never typecast" pattern for db rows and external json and architecture.
Command Claude Code
When user uses /cmt slash command, commit current git changes using fast mode by default, or strict mode when requested. Fast mode reviews, shows summary, and waits for approval. Strict mode adds safe simplifications, full /cr review, and verification before approval.
AaravKashyap12/advise-project-approach
Instructions file CodexOpenCode
AGENTS.md instructions for AaravKashyap12/advise-project-approach, covering repository guidance, source of truth, release discipline, maintainer agent roles and validation.
Skill Claude CodeCodex
Post-completion self-review for coding agents that runs simplify, harden, and micro-documentation passes on non-trivial code changes. Use when: a coding task is complete in a general agent session and you want a bounded quality and security sweep before signaling done. For CI pipeline execution, use…
Skill Claude CodeCodex
Review a GitHub pull request and post a verdict comment. Stateful — if a previous review comment exists, review only the new commits since the last review and track whether prior findings were addressed. Focus on code cleanliness, duplication, and docs sync. Use when user says "review this PR", "check the PR", "leave…
Skill Claude CodeCodex
Produce an evidence-grounded architecture review or design-decision critique — an architecture map, the painful complexity center, 3-6 chosen review lenses, ranked findings with file:line evidence, why-not alternatives, and a red/blue adversarial check — grounded in John Ousterhout's "A Philosophy of Software Design"…
leopiney/linus-torvalds-skills
Instructions file
Claude Code instructions for leopiney/linus-torvalds-skills, covering ai coding guidelines: torvalds doctrine, 1. data supremacy: the data structure is the design, 2. simplicity first: boring code is usually correct, 3. hardware truth: the machine sets the limits and 4. surgical changes: touch only what you must.
Skill Claude CodeCodex
Reviews code diffs, PRs, issue queues, release readiness, commits, pushes, publishing, and project audits. Use when users ask in any language for code review, issue or PR triage, release gates, publishing follow-through, or project audits. Not for debugging root causes or prose review.
Agent Claude Code
Python code quality — type hints, exception handling, modern idioms, dataclass/Pydantic patterns.
Instructions file
Claude Code instructions for Meridiona/meridian, covering meridian — claude code instructions, hard rules, file header requirement, repository layout and build, test, lint.
GoogleContainerTools/config-sync
Instructions file CodexOpenCode
AGENTS.md instructions for GoogleContainerTools/config-sync, covering agents.md, project summary, repository layout, build, test, lint and agent skills.
Skill Claude CodeCodex
Guides systematic code refactoring following the DRY (Don't Repeat Yourself) principle. Use when user asks to eliminate code duplication, refactor repetitive code, apply DRY principle, or mentions code smells like copy-paste, magic numbers, or repeated logic. Implements a 4-step workflow from identifying repetition to…
Skill Claude CodeCodex
Audit a policy/ / adapter for XPolicyLab standard compliance and PR readiness — file completeness, deploy.yml, Model contract, decodeimagebit-only decoding, script conventions, static checks, debug-mode eval, README and checkpoint requirements. Use when asked to check, validate, review, or pre-flight a policy adapter…
Skill Claude CodeCodex ✓ vendor
Create a new splinter lint — a SQL view that checks for a database anti-pattern. Use this skill when the user asks to add a lint, create a new check, implement a linting rule, or extend splinter with a new detection.
jens-duttke/usage-monitor-for-claude
Command Claude Code
Maintainer pre-merge gate - audit a PR (or staged changes), output review comments, then CHANGELOG entry.
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: