Overreach
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:
- Scope extraction (LLM) — one cheap call reads your prompt into structured JSON
- Diff parsing (deterministic) — regex-parses what the diff actually adds
- 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 agoUpdated At
7 days agoAuthor Name
Naveja00Star
-Tags
Recommend Clients
View AllPASTEAI
a month ago
STATIONONE
2 months ago
SUPERNORMAL
3 months ago
PACE
3 months ago
SOCIAL-API.AI
2 months ago
NOTE2IT
5 days ago
MCP-PEEK
6 days ago
CAPTAIN-CLAW
24 days ago
YESHELLO---DIGITAL-BUSINESS-CARDS
22 days ago
PGQ-PUBLIC-JUDGMENT-QUOTIENT
12 days ago
BETTERCLAW
a month ago
MCP-OAUTH2-PROXY
a month ago
NOVAMYND
15 days ago
VIDEO-TO-CLAUDE
a month ago