Borrowing it
Nothing to install: this file belongs to reunionstudio/airlock-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.
curl -O https://raw.githubusercontent.com/reunionstudio/airlock-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/reunionstudio/airlock-mcpWrote 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.
[](https://agentmods.dev/instructions/reunionstudio/airlock-mcp/agents-md)<a href="https://agentmods.dev/instructions/reunionstudio/airlock-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/reunionstudio/airlock-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00511 | $0.00511 |
| Opus 5 | $0.00255 | $0.00255 |
| Sonnet 5 | $0.00102 | $0.00102 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
airlock-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 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Airlock MCP Guidance
Airlock MCP is the single installed interface for AI agents working with Airlock. It should cover building specs, using specs, pulling and pushing governed data, and discovering improvements from real use cases.
Spec building is bundled inside Airlock MCP, not a second thing users install.
Product Boundary
- Keep this repo focused on connector installation, MCP server behavior, agent registration, Airlock-facing tools, spec drafting patterns, workspace files, and deterministic spec-building checks.
- The public user command is
npx @reunionstudio/airlock-mcp install. - For Codex, install should use
codex mcp add airlock -- npx -y @reunionstudio/airlock-mcp server. - After install, the user creates a blank
<project>-specsCodex project and starts chatting there. They should ask for Airlock, not for a separate spec-building install. - Current installed Airlock separates procedure intent:
observe.*is the read-only governance observation surface,agent.*is governed actor work, andadmin.*is administrative mutation. App and audit guidance should prefer observe payloads for discovery, health, access explanation, activity, billing events, governance maps, and context packets.
MCP Runtime
- The current Node server is a small bootstrap server for the one-install Airlock MCP experience.
- It documents, but does not proxy, the optional Snowflake-managed MCP
endpoints exposed by installed Airlock. Keep their fixed read-only tool and
identity boundary discoverable at
airlock://native-app-managed-mcp. - Prefer Rust with
rmcpfor the production MCP server once tools do real operational work beyond setup guidance, such as validating specs, loading records, reading outputs, handling attachments, or coordinating push/pull workflows. - For stdio MCP, stdout is protocol-only. Send logs and diagnostics to stderr.
- Test the stdio server with raw JSON-RPC messages for
initialize,tools/list,prompts/list,resources/list, andresources/read.
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.
- 6d ago First seen · 51 lines · 511 tokens per session scan A be0c77de6ffe
airlock-mcp AGENTS.md is an instructions file published in the GitHub repository reunionstudio/airlock-mcp (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 511 tokens to every session, about $0.0026 per session on Opus 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.