19,424 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.
MCP server Claude CodeCodexCursor +2
MCP server that acts as a contract linter for AI agents. Understand projects through structured YAML contracts instead of reading raw files. Runs locally from the @adaniki/contract-agent-linter npm package.
justfeltlikerunning/blastradius
MCP server Claude CodeCodexCursor +2
Dependency blast-radius analyzer: before you upgrade an npm package, see exactly which of YOUR files and functions touch its changed API surface. Runs locally from the @justfeltlikerunning/blastradius npm package.
Upendrasengar/bitbucket-server-mcp
MCP server Claude CodeCodexCursor +2
MCP server for Bitbucket Server / Data Center with code review, cross-repo PRs, and CI insights. Runs locally from the @upendra_sengar/bitbucket-server-mcp npm package.
adsorce/claude-reviewer-for-codex
Skill Claude CodeCodex
Use Claude as an independent second-model reviewer of Codex work. Supports normal and adversarial reviews, exact commit scope, working-tree or branch scope, explicit files, background jobs, wait-for-result delivery, status, result, and cancellation.
Cursor rule Cursor
Before finishing any code change, self-review against AGENTS.md rules.
Skill Claude Code
Comprehensive GitHub code review with AI-powered swarm coordination.
Skill Claude CodeCodex
Verify multi-repo agent claims at Git HEAD with GitPin (index-free evidence). Use for catalog, search candidates, pin.prove / pin.proveset, pin.verify / pin.verifyset, EvidenceBrief, and citation checks. Never treat dirty worktrees or search hits as claims.
Skill Claude CodeCodex
Use stash MCP to work with Bitbucket Server projects, repositories, and pull requests.
Skill Claude Code
Audit a chair's composed Insitu protocol for contradictions, unresolved references, stale doctrine, unneeded weight, and shape. Use when asked to audit, review, or trim a protocol, when a chair's core feels heavy or wrong, or when two loaded rules seem to disagree. Produces a proposal and never edits. Not for…
Skill Claude Code
Read-only security review of a web app's source, from an entry-point census to ranked findings with evidence and a named guard for every dismissal.
AaronLopezBarros/MCP_bitbucket
Skill Claude CodeCodex
Create, list, review, or comment on pull requests in Bitbucket. Use for any task related to PRs, Bitbucket, or code review — creating a PR, listing PRs, viewing diff/status/approvals, or adding comments to an existing PR.
Plugin Claude Code
Bundles 11 skills · 980 tokens together
11 skills for auditing a codebase: health-audit (scored, with separate grades for build quality and live harm), health-sweep (runs every applicable lens in parallel and merges the results), seven lenses (health-audit-ux, -api, -data, -domain, -dx, -ops, -seo), arch-audit (every violation of the codebase's own…
Skill Claude CodeCodex
Publish HTML pages, documents, files, or code changes to r3 for human review, and respond to feedback on existing r3 artifacts. Use when the user asks to use r3 or supplies an r3 artifact or feedback command.
Skill Claude CodeCodex
Audit the tool surface of an MCP server for discoverability, return-shape and naming consistency, error handling, test coverage, decay, state handling and, on multi-tenant servers, object-level authorization. Produces one evidence-only Markdown report that ends in a short list of named fixes of an hour or less and a…
Skill Claude CodeCodex
Delegate coding tasks to user-configured local coding agents such as Codex, Claude Code, OpenCode, Cursor Agent, Pi, or Copilot CLI.
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: