14,269 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.
Before merging or pushing, check whether your branch is compatible with other active branches. Use the Rosentic MCP tools: checkconflicts to scan for breaks, explainconflict for details, listbranches to see what's in flight.
Local-first CLI that mines git history for file-level co-change patterns and builds a queryable knowledge graph for AI coding agents, with optional enrichment from graphify's symbol/call-graph output when it is installed. Runs locally from the graphkeeper-cli Python package.
★not rated 0 2d agoA
tokens not measured
originalApache-2.0
Self-hosted GitHub MCP server. PAT auth, stdio transport, transport-agnostic so it works with Claude Code (any account), Codex CLI, Cursor, or any MCP-compliant client.
★not rated 0 3d agoA
tokens not measured
originalMIT
Use in any repository configured with Remogram (.remogram.json) or Remogram MCP for forge facts — PR status, checks, merge plan, repo status, ref compare. Not for Remogram product development.
Route GitHub engineering and MCP catalog questions to the correct BountyVerdict x402 decision API. Use for bounty selection, coding-agent instruction or skill audits, workflow diagnosis, flake retry gates, and tools/list compatibility or security checks before accepting a server change.
Saves, retrieves, and searches structured context (reasoning, decisions, trade-offs) behind AI-generated code, linked to git commits. Use when the developer says "save this session with GitWhy", asks about past context or decisions, or wants to push context to a PR. Also use after significant implementation work…
Working-memory shelf for Claude Code: the /shelve skill plus a SessionStart hook that injects the shelf INDEX (recall bootstrap) and a SessionEnd/PreCompact hook that pushes the shelf so episodes survive an ephemeral container.
★not rated 0 2d agoA
tokens not measured
originalMIT
Decentralized multi-agent coordination MCP: claim work, survey peers, detect conflicts, and reconcile via a git branch as compare-and-swap. Runs locally from the agentsync-mcp Python package. Needs 3 environment variables to run.
A commitment tripwire for AI-edited decision docs: flags when a tracked commitment disappears, word-for-word, between two versions — as a git pre-commit hook, a CLI, or an MCP server. A signal, not a judge. Runs locally from the aperture-mcp Python package.
★not rated 0 2mo agoA
tokens not measured
originalApache-2.0
Release & deploy gate for @kadam-net/mcp-server — what the agent may do autonomously vs. what requires explicit human approval. Applies to all branch/MR/release/deploy work in this repo.
Trigger: after you edit files / complete code changes in a git repo. Call the showdiffexplanation MCP tool to auto-explain the git diff. Do NOT trigger for read-only questions or when nothing changed.
Test management over MCP: author cases, run manual executions, cut releases, read health. Runs locally from the @m00nsolutions/mcp-server npm package. Needs 5 environment variables to run.
★not rated 0 20d agoA
tokens not measured
originalMIT
Create, update, and publish changelog entries on your Patchlog changelog from any MCP client. Runs locally from the patchlog-mcp npm package. Needs 2 environment variables to run.
★not rated 0 29d agoA
tokens not measured
originalMIT
Read, create, update and delete gists on a self-hosted Opengist instance. Runs locally from the opengist-mcp npm package. Needs 6 environment variables to run.
★not rated 0 3d agoA
tokens not measured
originalMIT
Use for git module dependencies, a2amodule.yml, dependency owners, contacts, status, and the managed AGENTS.md roster.
★not rated 0 18d agoA32 tokens
originalMIT
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: