agentmods.dev

repo-contract

repo-contract is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from dager23/RepoContract. Its token cost is not measured, scanned A, original, MIT.

A local MCP server that acts as a governance layer for coding repositories. It checks plans and code changes against machine-readable repository rules.

In plain words
What is it for?
Use it when a repository needs automated checks for proposed work and code changes.
Why use it?
It helps apply project requirements consistently instead of relying only on a developer or coding agent to remember them. The description does not list the specific checks it performs.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Written for no agent in particular: it speaks MCP, so any client can run it.

not rated 1 1mo ago A scan tokens not measured original MIT
View the source file dager23/RepoContract
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add mcp/dager23/repocontract/repo-contract
Clone the repo
git clone --depth 1 https://github.com/dager23/RepoContract

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for repo-contract

README.md
[![agentmods](https://agentmods.dev/badge/mcp/dager23/repocontract/repo-contract.svg)](https://agentmods.dev/mcp/dager23/repocontract/repo-contract)
Your own site
<a href="https://agentmods.dev/mcp/dager23/repocontract/repo-contract"><img src="https://agentmods.dev/badge/mcp/dager23/repocontract/repo-contract.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

repo-contract scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

listed in the official MCP registry · 8 lines

What it actually says

{ "repo-contract": { "command": "uvx", "args": [ "repo-contract" ] } }

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 8 lines scan A 4d74d67f4d36

Subscribe to this mod's changes

repo-contract is an MCP server published in the GitHub repository dager23/RepoContract (1 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsCode reviewaiclaude-codecursordeveloper-toolsgovernancemcp
Related

Other mcp servers, from other repositories

agent-guardrails

Local merge gates for AI coding agents with scope, validation, risk, and review evidence. Runs locally from the agent-guardrails npm package.

logi-cmd/agent-guardrails · not measured

forensic-deepdive

Forensic deep-dive of any codebase (9 languages). Persistent code knowledge graph + MCP server (9 composite tools incl. hybrid NL query, Mermaid export & cross-stack trace) for AI coding agents, with 5 durable markdown artifacts (MAP, HOTPATHS, ARCHAEOLOGY, MENTALMODEL, AGENTBRIEF) as the human-readable projection.…

Dhevenddra/forensic-deepdive · not measured

audit

Score any public GitHub repo 0-100 against the commit.show audit rubric. Runs locally from the commitshow-mcp npm package.

commitshow/cli · not measured

forgecraft

CLI + MCP sentinel for engineering standards — SOLID, testing, architecture, CI/CD — auto-tailored to your stack. Minimal MCP footprint (200 tokens) via CLI-first design. Runs locally from the forgecraft-mcp npm package.

jghiringhelli/forgecraft-mcp · not measured

pr-narrator-mcp

MCP server for generating consistent commit messages and PR content based on your custom criteria. Runs locally from the pr-narrator-mcp npm package.

mhaviv/pr-narrator-mcp · not measured

code-quality

MCP server for code quality: complexity, duplicates, naming, refactoring. Runs locally from the sovereign-code-quality-mcp npm package.

ryudi84/sovereign-mcp-servers · not measured