Overreach

Created By
Naveja0012 days ago
Overreach catches AI-agent scope creep. You give it the prompt you gave your coding agent and the diff it produced; it flags every part of the diff the prompt didn't authorize — unauthorized dependencies, env vars, endpoints, cron jobs, files, and features. Every finding is deterministic set arithmetic (actual − authorized), not a probabilistic opinion. Ships a GitHub Action that fails PRs on scope_creep_score=HIGH. MIT, free to use.
Overview

Overreach audits AI-agent code diffs against the prompt that authorized them. Give it the prompt you gave your coding agent and the diff it produced — it tells you exactly what the agent added that wasn't in scope.

Catches: unauthorized dependencies, env vars, endpoints, cron jobs, out-of-scope files, features the prompt never mentioned.

3-stage pipeline:

  1. Scope extraction (LLM) — one cheap call reads your prompt into structured JSON
  2. Diff parsing (deterministic) — regex-parses what the diff actually adds
  3. Comparison (deterministic) — set arithmetic: actual - authorized = findings

No API key required. Falls back to deterministic regex extraction without a key.

Try it: npx -y -p overreach overreach-cli demo

Also coordinates multiple AI agents on the same repo — file claims, conflict detection, scope declarations, check-in heartbeats. Works across Claude Code, Cursor, and Codex simultaneously. Just JSON files committed to git, no server.

Server Config

{
  "mcpServers": {
    "overreach": {
      "command": "npx",
      "args": [
        "-y",
        "-p",
        "overreach",
        "overreach"
      ]
    }
  }
}
Project Info
Created At
12 days ago
Updated At
7 days ago
Author Name
Naveja00
Star
-
Category

Recommend Clients

View All
PACE

3 months ago
BETTERCLAW

a month ago
ZENGLIANGYI

17 days ago
ENCONVERT-MCP

2 months ago
ENSEMBLE-MCP

13 days ago
NIBWP

2 days ago
E2EASY

2 months ago