Borrowing it
Nothing to install: this file belongs to airutorg/airut. 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/airutorg/airut/main/CLAUDE.mdgit clone --depth 1 https://github.com/airutorg/airutWrote 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/airutorg/airut/claude-md)<a href="https://agentmods.dev/instructions/airutorg/airut/claude-md"><img src="https://agentmods.dev/badge/instructions/airutorg/airut/claude-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.
<a href="https://agentmods.dev/instructions/airutorg/airut/claude-md"><img src="https://agentmods.dev/badge/instructions/airutorg/airut/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03702 | $0.03702 |
| Opus 5.5 | $0.01481 | $0.01481 |
| Sonnet 5.5 | $0.00740 | $0.00740 |
| Haiku 4.5 | $0.00370 | $0.00370 |
Grade A, and why
airut CLAUDE.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 1mo 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Operating Instructions for Airut
Project Overview
Airut is a self-hosted gateway that runs sandboxed Claude Code over email and Slack. Named "Airut" (Finnish: herald/messenger).
Network requests from containers are sandboxed; if requests fail, check
.airut/network-allowlist.yaml. See doc/network-sandbox.md for details.
Documentation
High-level documentation in doc/ (see doc/README.md for full list):
doc/architecture.md— system architecture and data flowdoc/security.md— security model (channel auth, isolation, credentials)doc/execution-sandbox.md— container isolation and resource limitsdoc/network-sandbox.md— network allowlist and proxy architecturedoc/ci-sandbox.md— sandboxing GitHub Actions and CI pipelinesdoc/deployment.md— installation and server configurationdoc/github-app-setup.md— GitHub App setup for agent identitydoc/email-setup.md— email channel setup (IMAP/SMTP, DMARC)doc/slack-setup.md— Slack channel setup (Socket Mode, authorization rules)doc/m365-oauth2.md— Microsoft 365 OAuth2 setup for email (IMAP/SMTP)doc/repo-onboarding.md— onboarding new repositoriesdoc/gerrit-onboarding.md— Gerrit-specific onboardingdoc/agentic-operation.md— message-to-PR workflow patternsdoc/periodic-tasks.md— cron-triggered scheduled tasks with email deliverydoc/testing.md— test strategy, coverage enforcement, config migration testing
Implementation specs in spec/ (see spec/README.md for full list):
spec/gateway-architecture.md— core gateway design, channel abstraction, data flow, container executionspec/authentication.md— DMARC verification and sender authorizationspec/repo-config.md— per-repo schema in server configspec/declarative-config.md— declarative config layer (schema metadata, migration, diffing, round-trip, config variables)spec/config-reload.md— live config reload (file watching, scope-aware application, deferred reload)spec/multi-repo.md— multi-repository support designspec/slack-channel.md— Slack channel implementation (Socket Mode)spec/integration-tests.md— end-to-end test specificationspec/periodic-tasks.md— cron-triggered periodic tasks (scheduler, prompt/script modes, email delivery)spec/sandbox.md— sandbox library for safe containerized Claude Code executionspec/sandbox-action.md— reusable GitHub Action wrapping airut-sandboxspec/sandbox-cli.md— standalone sandbox CLI for CI and other environmentsspec/image.md— two-layer container image build strategyspec/network-sandbox.md— proxy lifecycle, resource scoping, log format, crash recoveryspec/masked-secrets.md— scope-restricted credentials with proxy-level token replacementspec/aws-sigv4-resigning.md— AWS SigV4/SigV4A credential masking via proxy re-signingspec/request-body-filters.md— request-body filter pipeline (shared structure for service-specific payload filtering at the proxy layer)spec/graphql-operation-allowlist.md— generic GraphQL operation filtering at the proxy layerspec/anthropic-tool-domain-trim.md— proxy-side trimming of Anthropic server-side-toolallowed_domainsto the airut network allowlistspec/github-app-credential.md— GitHub App credential support with proxy-managed token rotationspec/dashboard.md— web dashboard for task monitoringspec/cli.md— CLI subcommands, service management, self-updatespec/pr-workflow-tool.md— PR workflow automation (ci.py, pr.py)spec/local-ci-runner.md— CI runner (single source of truth for all CI checks)
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.
- 1mo ago First seen · 369 lines · 3,702 tokens per session scan A c9f4d2e70beb
airut CLAUDE.md is an instructions file published in the GitHub repository airutorg/airut (84 stars, last pushed today), licensed MIT. It adds 3,702 tokens to every session, about $0.0148 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 2026-08-30.
Other instructions, from other repositories
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).