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/mazze93/github-mcp-gateway/agents-mdgit clone --depth 1 https://github.com/mazze93/github-mcp-gatewayWhat 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 | $0.00222 | $0.00222 |
| Opus 5 | $0.00111 | $0.00111 |
| Sonnet 5 | $0.00044 | $0.00044 |
| Haiku 4.5 | $0.00022 | $0.00022 |
Grade A, and why
github-mcp-gateway 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 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
AGENTS.md
This file is intentionally a pointer, not a copy.
Read CLAUDE.md — it is the single source of truth for
how to work in this repository, and it applies to every coding agent
regardless of vendor. Commands, architecture, the tool-adding pattern,
constraints, and recovery steps all live there.
Why this is a pointer
AGENTS.md previously duplicated CLAUDE.md with the client names
find-replaced. The two then drifted, as duplicated instructions always
do: the copy went on telling agents that npm run deploy was the deploy
path months after CI took that over, described a repo with no test
suite, and referred to a product called "Codex.ai/Cowork" that does not
exist.
An agent reading stale instructions confidently does the wrong thing. One file that is right beats two that disagree.
If you maintain another agent's config
Point it at CLAUDE.md rather than forking a copy here.
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 · 25 lines · 222 tokens per session scan A d1e519bab6f5
github-mcp-gateway AGENTS.md is an instructions file published in the GitHub repository mazze93/github-mcp-gateway (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 222 tokens to every session, about $0.0011 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
vibesdk AGENTS.md
AGENTS.md instructions for cloudflare/vibesdk, covering agents.md, tooling, verification, frontend ui and frontend data fetching.
vibesdk CLAUDE.md
Claude Code instructions for cloudflare/vibesdk, covering claude.md, communication style, project overview, key architectural patterns and common development tasks.
munkel CLAUDE.md
Instructions for limehq/munkel, covering claude.md, monorepo layout, commands, macos development specifics and deploy.
cloudbox AGENTS.md
Instructions for acoyfellow/cloudbox, covering cloudbox agent guide, canonical commands, deploy model, cloudflare account boundaries and required production secrets.
ctxlayer CLAUDE.md
Instructions for stevenn/ctxlayer, covering ctxlayer — claude code briefing, what runs where, architecture pointers, how a claude session should work in this repo and conventions.
ctxlayer AGENTS.md
Instructions for stevenn/ctxlayer, covering working in this repo as an agent, golden path for any change, where things live, module rules and adding an endpoint.