17,650 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 Code
Markdown-first, AI-native parent skill for one repo-level Loop9 repo-complete loop. Use when you want the parent layer to hold repo-level owner, repo truth relocation, full finding-queue completion, repo-level closure, and final deliverable-oriented verdict while dispatching only thin handoffs to env-bootstrap /…
Plugin Claude Code
Bundles 7 skills, 7 commands · 168 tokens together
SOLID design auditor and fixer for Claude Code. Audit changed files for violations and apply behavior-preserving fixes.
Plugin Claude Code
Bundles 17 skills, 14 agents · 813 tokens together
Production-grade Claude Code Agent Teams harness with adversarial review, competing-hypothesis debugging, and pair building.
thomast1906/github-copilot-sdk-github-action-example
Skill Claude CodeCodex
You are an expert code reviewer with deep knowledge of software engineering best practices, security, and performance optimization.
Skill Claude CodeCodex
Use when Claude wants an adversarial review, design critique, plan critique, or second-opinion debugging from Codex AND wants to engage with the findings rather than receive a one-shot report. Sets up an Epic bead, asks Codex to file each finding as a child bead, then runs a back-and-forth where Claude responds to…
Lagunaswift/GameDevelopmentAudit
Skill Claude CodeCodex
Use this skill when a game or repo has too many mechanics, too much special-case code, or shallow gameplay despite lots of content. Trigger on: 'my game feels bloated', 'should I cut this mechanic', 'my codebase is full of special cases', 'players found an exploit/dominant strategy', 'balance review', 'the game is…
Agent Claude Code
Expert Claude Code skill reviewer that validates skills against official Anthropic specifications AND effectiveness for auto-invocation with deterministic scoring. Use PROACTIVELY after creating or modifying any SKILL.md file to ensure compliance with official requirements AND that the skill will actually be…
Cursor rule Cursor
What an AI reviewer should and should not flag. Keeps review high-signal.
chenxihuang1028-a11y/variant-analysis
Skill Claude CodeCodex
Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL/Semgrep queries, analyzing security vulnerabilities, or performing systematic code audits after finding an initial issue.
cyberash-dev/coding-agent-config
Skill Codex
Review a supplied code change or explicit file set using all applicable contextual, repository, language, and quality rules. Use whenever Codex is asked to review, audit, or inspect code in the app, CLI, IDE, automation, or another review adapter. Do not implement fixes unless the user explicitly changes the task.
Cursor rule Cursor
Principal-level code review checklist — run before any release is cut.
Skill Claude CodeCodex
Code-reviews Pluggy API integrations against Pluggy's official documentation (queried in real time via the Pluggy MCP, with a web fallback to docs.pluggy.ai when the MCP isn't connected) and returns a diagnostic report (✅/❌/⚠️) with file, line, and the code fix for each issue. Use WHENEVER the dev uploads integration…
Skill Claude CodeCodex
General pull-request review criteria, severity scale, and comment format. Load on every PR review to keep findings consistent, actionable, and low-noise.
Skill Claude CodeCodex
Use when coding, designing, reviewing, or writing documentation in TypeScript or Python projects.
Skill Claude CodeCodex
Have Claude Fable 5 plan the current task, then run an automatic warm diff-review after you execute. You (the below-Fable driver — Sonnet or Opus) gather the evidence and execute; Fable is the context-blind PLANNER — one plan engagement at the start (it writes the plan, unanchored by any draft of yours), one warm…
Cursor rule Cursor
Anti-patterns to avoid - common mistakes that lead to poor code quality and technical debt.
Plugin Claude Code
Bundles 11 skills, 1 hook · 825 tokens together
Socratic lenses for software engineering: question batteries that examine your work from security, design, usability, test-quality, and operational-recovery perspectives — plus an orchestrator that surfaces caveats, rabbit holes, and blast radius before you build, and a memory loop that grows new lenses from your real.
Agent Claude Code
Reviews Swift/SwiftUI code for quality, security, and performance. Use after any code changes.
bingshuoguo/linus-torvalds-skills
Cursor rule Cursor
Linus-inspired behavioral guidelines for code review, design risk analysis, implementation taste, simplicity, and backward compatibility.
get-convex/convex-codex-plugin
Skill Claude CodeCodex
Review Convex code for security, auth, validators, performance, and best practices. TRIGGER when the user asks to review/audit Convex code, or after writing convex/ functions you want checked. Applies the Convex-specific review checklist (auth checks, args/returns validators, internal vs public, indexes-not-filter…
Skill Claude CodeCodex
Refactor and code review across hygiene, over-engineering, runtime lenses. Supports target review and uncommitted-changes review. Reconciles conflicts, checks churn, emits ordered work units, uses language overlays.
Skill Claude CodeCodex
Generate comprehensive summaries of pull request changes by comparing the current branch to main, or by analyzing an existing PR by number. Use when the user asks to summarize changes, preview what's in a PR, or understand what work has been done. Triggers include "summarize my changes", "what's in this PR?", "give me…
Skill Claude Code
Review code changes using parallel agents. Works on local diffs or open PRs. Checks project conventions, scans for bugs, verifies claims, and resolves review threads. Use when the user says "review", "review this", "review PR", "check this PR", or invokes /review.
Skill Claude Code
Use when reviewing Go, Python, or TypeScript code for classic code smells, preparing a refactor, auditing code after rapid feature development, or hunting for misplaced responsibilities and undermodeled domain concepts. Covers feature envy, data clumps, shotgun surgery, temporal coupling, comments as deodorant…
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: