Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/trivo25/code-airlock/claude-mdgit clone --depth 1 https://github.com/Trivo25/code-airlockWhat 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 | $0.00010 | $0.00010 |
| Opus 5 | $0.00005 | $0.00005 |
| Sonnet 5 | $0.00002 | $0.00002 |
| Haiku 4.5 | $0.00001 | $0.00001 |
Grade A, and why
code-airlock 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 2d 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.
What it actually says
Read AGENTS.md for repo instructions.
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.
- 2d ago First seen · 2 lines · 10 tokens per session scan A 7077254e3317
code-airlock CLAUDE.md is an instructions file published in the GitHub repository Trivo25/code-airlock (20 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session, about $0.0001 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 2026-08-30.
Other instructions, from other repositories
mosoo AGENTS.md
Instructions for langgenius/mosoo, a project described as: The open-source Agent Gallery and Gateway for Codex, Claude Agent SDK, and OpenCode. Developers publish an Agent once behind one HTTP API; users run it in an isolated cloud sandbox—no local harness setup, compute, or runtime infrastructure.
talkcody AGENTS.md
Instructions for talkcody/talkcody, covering project development guide for ai agents, project overview, architecture diagram, technology stack and frontend.
ai-website-cloner AGENTS.md
Instructions for UHolli/ai-website-cloner, covering this is not the next.js you know, website reverse-engineer template, what this is, tech stack and commands.
CluxMate AGENTS.md
Instructions for r1c7/CluxMate, covering project memory, what cluxmate is, architecture — core invariants, security: sandbox (read the docs before touching this code) and hooks.
AI-AGENT-SKILLS AGENTS.md
AGENTS.md instructions for vignesh2027/AI-AGENT-SKILLS, covering agent skills — execution model, core principle, skill discovery, command → skill mapping and always active rules.
AI-AGENT-SKILLS CLAUDE.md
Claude Code instructions for vignesh2027/AI-AGENT-SKILLS, covering ai agent skills — claude instructions, what this repo is, contribution rules, skill files must and what to avoid.