GOVENANT
Free · read-only · Coding tool

Audit your Claude Code agents.

Audit the AI agents in your codebase from Claude Code in one command. Add the GOVENANT Audit MCP server, sign in from the terminal, and have Claude Code run a read-only trust sweep that maps your substrate to the standard automatically.

Add it to Claude Code → Read the FAQ
Step 1

Add the audit to Claude Code

Paste one URL — no API key. Claude Code connects itself.

Step 2

Sign in

Browser sign-in via the /mcp command. That’s the whole ask.

Step 3

Ask for the audit

Say “Run a GOVENANT trust sweep.” Get a shareable report back.

Add the GOVENANT Audit to Claude Code

The MCP server URL:

https://mcp.govenantstandard.org/mcp

Run this command:

claude mcp add --transport http govenant https://mcp.govenantstandard.org/mcp
  1. Run: claude mcp add --transport http govenant https://mcp.govenantstandard.org/mcp
  2. Run /mcp inside Claude Code to sign in (browser opens).
  3. Add --scope user to the command to enable GOVENANT in every project.
  4. Ask Claude Code: “Run a GOVENANT trust sweep.”

Authentication: Browser sign-in via the /mcp command.

What the Claude Code audit tells you

Anomalies first

The bad news up top: motion without delivery, missed work, approvals expiring unapproved, decisions never graded — the signs of performed autonomy.

Your grade

Where your Claude Code agents land on the GOVENANT ladder — Logged → Gated → Delivered → Earned — and the delivery numbers behind it.

Delivery, not activity

Verified outcomes vs. total actions, work delivered vs. missed — measured against the record, never self-reported.

A shareable page

Every run has its own URL, with an optional one-click “share for a free expert review.”

Claude Code audit — FAQ

How do I enable it across all my projects?
Add --scope user to the `claude mcp add` command and the GOVENANT server is available in every Claude Code project, not just the current repo.
What does Claude Code actually read?
Your own agent runs the read-only battery — aggregate counts, ratios, timestamps, and model names from your system’s records. It never transmits source, prompts, or secrets.
Is the GOVENANT Audit really free?
Yes. You sign in with GitHub or Google so we know who ran it — that’s the whole ask. No API key, no credit card, no paywall on the audit.
What does it read, and what does it never see?
It reads aggregate numbers from your agents’ own records: how many ran, how many finished, whether checks passed, which models you use. It never reads your prompts, your agents’ messages, your customers’ data, or any secrets.
What is “performed autonomy”?
Agents that look busy — fluent plans, satisfied logs — but don’t verifiably ship. Motion is not delivery. The audit measures verified outcomes against the record, never the logs’ self-report.

Using a different tool?

Claude DesktopChatGPTCursorVS Code (Copilot)WindsurfCodex CLICline

Prove your agents actually deliver.

Free under the covenant — the method is free forever. Read-only and aggregate-only: your prompts, data, and secrets never leave your machine.

Add it to Claude Code → See it audited on itself