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.
nexicturbo/github-pr-control-mcp
MCP server Claude CodeCodexCursor +2
A production-ready MCP server for triaging and reviewing GitHub pull requests. Runs locally from the github-pr-control-mcp npm package.
MCP server Claude CodeCodexCursor +2
Design graph for hexagonal-architecture codebases. Renders what a branch changed as one picture a human can confirm at a glance, and gives a coding agent boundary verdicts it can run on itself before asking for review. Runs locally from the hexwright npm package.
Skill Claude CodeCodex
Semantic code intelligence for third-party libraries via the xmp4 MCP server (SCIP-backed, covers CSharp, TypeScript, Python, Java, Rust, PHP, Go, JavaScript, Dart, Ruby, C++). Use this skill whenever the user asks to explore, navigate, or understand an OSS or third-party library — find how an API is actually used…
MCP server Claude CodeCodexCursor +2
Consult a multi-model panel on contested decisions via MCP: architecture, plan review, strategy. Remote server at mumo.chat.
MCP server Claude CodeCodexCursor +2
LineBreak security gate at the git/CI boundary: dependency CVE scan + AI SAST, human-approved overrides, git-native audit records. Runs locally from the linebreak-gate Python package.
MCP server Claude CodeCodexCursor +2
One of 2 in server.json
Architecture audit MCP server — submit architecture docs from any AI coding agent and get back a consulting-grade traceability audit at a shareable URL. Runs locally from the archiet-audit-mcp Python package. Needs 1 environment variable to run.
CSOAI-ORG/code-reviewer-ai-mcp
MCP server Claude CodeCodexCursor +2
Code Reviewer Ai MCP server. Tools: review code, check security, suggest improvements. Built by MEOK AI Labs. Runs locally from the code-reviewer-ai-mcp Python package.
ChristopherDavenport/github-twin
Plugin Claude Code
Personal RAG over your GitHub history (commits, code, review comments), served to Claude Code over MCP. Tools: findcode, findreviews, predictreviewoutcome, houserules, developerprofile, and related retrieval surface.
MCP server Claude CodeCodexCursor +2
Evidence-backed architecture-quality analysis for Python agent applications. Runs locally from the uptocode Python package.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 60 tokens together
Independent static verification for immutable public GitHub commits.
Skill Claude CodeCodex
Deep technical audit of a React codebase via the Dendro MCP server — complexity hotspots, circular deps, rerender risks, actionable recommendations. Triggers: /dendro-audit, 'audit this React codebase', 'dendro audit'.
MCP server Claude CodeCodexCursor +2
The code-review MCP that reviews your merge request against the whole codebase, not just the diff. Runs locally from the myopic Python package.
MCP server Claude CodeCodexCursor +2
Paid dev services for AI agents: code review, bug-fix, tests, docs, audits. USDC on Base x402. Remote server at brain.zugabot.ai.
Skill Claude CodeCodex
Run Evolith architecture validation and report a coverage-honest verdict. Use when asked to validate architecture, check ADR compliance, run architecture or governance rules, check an SDLC phase gate, or answer "does this repo pass architecture review". Also before merging, releasing or promoting a phase. Reports…
choreoatlas/over_reach_detector
MCP server Claude CodeCodexCursor +2
Detect when AI code changes exceed declared task scope (MCP server). Runs locally from the over-reach-detector Python package.
Plugin Claude Code
Bundles 8 skills · 526 tokens together
8 Claude Code skills that run on a cadence to fight code entropy — method brevity, naming clarity, duplication detection, broken windows. See cdd.dev/skills/hone.
detailobsessed/codereviewbuddy
MCP server Claude CodeCodexCursor +2
codereview buddy helps your AI agent interact with AI code review--smoothly! Runs locally from the codereviewbuddy Python package.
Skill Claude CodeCodex
Verify AI-generated code before shipping. Run Umbra's Trust Score scan before committing or finishing any coding task, treat findings as blocking issues, and re-scan until clean. Use when finishing a task, before a commit, or when reviewing code written by an agent.
MCP server Claude CodeCodexCursor +2
The toolbox for AI agent skills: scaffold, lint, pack, install, and serve SKILL.md skills with a built-in MCP server. Runs locally from the skillkit-cli Python package.
MCP server Claude CodeCodexCursor +2
Screens public GitHub repos and PRs to generate risk maps, findings, and merge-readiness signals. Remote server at mcp-github-screen.gitlumen.com.
MCP server Claude CodeCodexCursor +2
Whole-repo code graph for AI agents: impact analysis, dead code, cycles, semantic search — 14 tools. Remote server at mcp.idencify.com.
MCP server Claude CodeCodexCursor +2
Code-as-graph for safe LLM-assisted development. Runs locally from the lenspr Python package.
MCP server Claude CodeCodexCursor +2
Code intelligence MCP: symbols, call graphs, change impact + affected tests, routes, search. Runs locally from the @lusiem/code-atlas npm package.
MCP server Claude CodeCodexCursor +2
Breaking-change diffs for npm packages: removed exports, changed signatures, migration notes. Runs locally from the vdiff-mcp npm package. Needs 1 environment variable to run.
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: