What is compass-mcp AGENTS.md?

Repository instructions for a read-only bridge to Compass, a public repository of profiles, manifests, and skill documents. They specify how the bridge should retrieve one consistent version of that content.

Use them when building, testing, deploying, or verifying the Compass MCP bridge.

They prevent deployments from mixing revisions, changing repository data, storing user information, or running unapproved code.

How ariobarin/compass-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to ariobarin/compass-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ariobarin/compass-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/ariobarin/compass-mcp

Made for: Codex, 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ariobarin/compass-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/ariobarin/compass-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ariobarin/compass-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ariobarin/compass-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ariobarin/compass-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ariobarin/compass-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 169 This file is loaded in full into every session.

When invoked 169 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00169	$0.00169
Opus 5.5	$0.00068	$0.00068
Sonnet 5.5	$0.00034	$0.00034
Haiku 4.5	$0.00017	$0.00017

Measured 2mo ago against content hash 4ec18fa2140f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

compass-mcp AGENTS.md 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 2mo 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.

AGENTS.md · 12 lines

What it actually says

Repository guidance

Compass MCP is the read-only ChatGPT bridge for the public ariobarin/compass repository.

Keep Compass content in Compass. This repository owns transport, revision pinning, freshness checks, and deployment only.

For every MCP request, resolve one Compass revision and load every profile, manifest, and skill document from that exact revision. Never bundle a mutable Compass snapshot into a deployment and never mix main reads with revision-pinned reads.

Before committing, run npm audit --audit-level=moderate, npm run build, npm test, and npm run smoke:worker. After deployment, run npm run smoke:remote and npm run verify:remote.

Keep the server read-only. Do not add repository mutation, shell execution, credentials, user-specific state, or model calls.

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.

2mo ago First seen · 12 lines · 169 tokens per session scan A 4ec18fa2140f

Subscribe to this mod's changes

compass-mcp AGENTS.md is an instructions file published in the GitHub repository ariobarin/compass-mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 169 tokens to every session, about $0.0007 per session on Opus 5.5. 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.

compass-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
compass-mcp AGENTS.mdariobarin/compass-mcp	Instructions file	0	21d ago	MIT	A	169	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

compass-mcp: Instructions file for Codex