19,479 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 Codex
Plan, install, inspect, update, or roll back Rootloom Personal Core in a user's Codex home. Supports Skills-only, guidance, and the recommended personal preset. Use when the user explicitly asks for a Rootloom setup plan, installation, configuration, bootstrap, repair, audit, status, update, reduction, rollback, or…
Skill Codex
Audit, grade, rewrite, and issue funny evidence-backed tickets for generic AI-slop patterns in prose, social posts, UI/design, and code. Use when asked to de-slop writing, humanize AI copy, grade a draft, review a landing page or generated interface, remove vague claims and repetitive rhetoric, inspect AI-written code…
MCP server Claude CodeCodexCursor +2
MCP server "ducklab" as configured in jrullan/ducklab. Launched with https://github.com/jrullan/ducklab/releases/download/v0.7.0/ducklab-mcp.mcpb.
Skill Claude CodeCodex
Full feature workflow: branch, implement, check, review, PR, merge, release. Use for "let's add X" or "ship this". Single git steps go to git.
LichAmnesia/awesome-antigravity-skills
Skill Claude CodeCodex
Generates a reviewer-friendly pull request description from the branch diff. Use when opening a PR, when asked to summarize a branch, or before requesting review.
Skill Claude CodeCodex
Reviews the code changes in your pull request.
Plugin Claude Code
Bundles 2 skills · 634 tokens together
Comprehensive PR review pipeline: a pre-review readiness gate (stops on merge conflicts or red code-related CI with a fix-it note, no verdict), branch-level analysis with merge-base attribution (the verdict is decided only by defects the diff introduced, worsened, or interacts with — purely pre-existing defects are…
Plugin Cursor
Bundles 31 skills, 1 MCP server · 1,499 tokens together
ControlKeel governance for Cursor — validation, findings, budgets, proofs, memory, agent routing, and human review via MCP.
Skill Claude CodeCodex
One tick of the GitHub maintenance loop for the repository named in .loop/config.json: send what the maintainer already approved, triage the issues created in the configured window, fix what is worth fixing test-first, follow the owner's own pull requests through CI, review and merge, and draft every outbound action…
layered-ai-public/claude-review-action
Command Claude Code
Review the current branch against the base branch.
Plugin Claude Code
Bundles 26 skills, 33 commands, 6 agents, 8 hooks · 2,901 tokens together
Research gated development: researcher, swiper and the bad-cop and good-cop review loop, plus the skills and slash commands that drive them.
Skill Codex
Review code against CODINGSTANDARDS.md and applicable repository rules, and check for defects. Use for PR, branch, commit, working-change, file, or repository reviews, including an optional interview to create missing standards or explicitly requested standards updates. Not for implementing fixes or a standalone audit…
wiolett-industries/marketplace
Plugin Claude Code
Bundles 1 skill, 4 agents · 170 tokens together
A risk-budgeted ready GitLab MR review for Claude Code with discussions first, CI-first evidence, zero-agent normal review by default, bounded high-risk agents, focused delta re-review, and one clean-pass approval. Uses a separately configured authorized GitLab interface for GitLab reads/writes.
Command Claude Code
Run sequential code review passes with fresh contexts to catch more issues.
Plugin Claude Code
Bundles 1 skill · 38 tokens together
Offline TypeScript/JavaScript analysis, grep, similarity detection, and project tree views.
Skill Claude CodeCodex
Run an LLM council — Claude (correctness), Gemini (edge cases), Cursor (integration), Kilo (maintainability), and you (scope) tackle the same task in parallel. Use when the user wants multiple independent perspectives on a decision, approach, or problem.
Agent Claude Code
Use this agent when you need comprehensive manual quality review, integration testing, and user experience validation. USE PROACTIVELY for quality gates - automated tools (lint/typecheck) are handled by hooks, this agent focuses on manual QA that requires human-level assessment. Examples: Context: User has just…
Command Claude Code
Triple-provider adversarial review — Codex + Gemini + Claude synthesis.
LetheChen/openclaw-longmen-inn
Skill Claude CodeCodex
A software quality and release-checking guide for reviewing code, testing applications, checking performance, and verifying delivery materials.
Skill Claude Code
Discover what to build next across a whole product: fan out parallel agents to map the current repo into a feature inventory, research competitors, ideate across seven value lenses, dedup and shortlist, spec and adversarially validate the winners, then synthesize a ranked roadmap. Distinct from brainstorm, which goes…
Skill Claude Code
Read a dxkit report and execute fixes — prioritize findings by severity, plan the fix sequence, run the fix, verify the score moved, re-baseline if appropriate. Supports a SCOPED pass to burn down one category at a time (dependency/BOM vulnerabilities, security, code quality, tests, docs), and a BASELINE-CLEANUP pass…
Command Claude Code
You are a panel of 8 independent expert reviewers. Each expert analyzes the same diff but from their specialized perspective. Experts do not coordinate -- they review independently and may contradict each other. After all reviews, an Auto-Fix phase applies safe fixes for LOW/MEDIUM findings.
asap-protocol/agentic-orchestration
Command Claude CodeCursor
You are a senior security engineer conducting a focused security review of the changes on this branch.
Skill Claude Code
Scan React codebase for useEffect anti-patterns (derived state, event logic in effects, effect chains, prop-driven resets, missing cleanup, parent notifications, etc.) and propose idiomatic fixes. Based on React's "You Might Not Need an Effect" guide. Use when asked to audit, review, or clean up useEffect usage.
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: