Borrowing it
Nothing to install: this file belongs to ratel-ai/ratel-local. 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/ratel-ai/ratel-local/main/AGENTS.mdgit clone --depth 1 https://github.com/ratel-ai/ratel-localWrote 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/ratel-ai/ratel-local/agents-md)<a href="https://agentmods.dev/instructions/ratel-ai/ratel-local/agents-md"><img src="https://agentmods.dev/badge/instructions/ratel-ai/ratel-local/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 | $0.00474 | $0.00474 |
| Opus 5 | $0.00237 | $0.00237 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
ratel-local 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.
What it actually says
AGENTS.md
Guidance for coding agents working on Ratel Local — the MCP gateway that fronts
Claude Code / Codex / Cursor with capability search. Shipped as @ratel-ai/ratel-local.
pnpm workspace: packages/core, packages/ui, apps/ratel-local, e2e/.
Setup
- Node 24+, pnpm 10+.
pnpm install
Core commands
pnpm build # tsc → dist/
pnpm typecheck
pnpm lint # biome
pnpm test # vitest
CI (.github/workflows/ts.yml) runs all four on every PR. Land green.
Rules
- TDD on library and CLI logic. Red → green → refactor (vitest).
- Conventional-commits-ish prefixes:
feat:,fix:,chore:,docs:,refactor:,ci:. Scopes optional but useful (fix(cli):). - No tool-attribution lines in commit messages (no
Co-Authored-By: Claude, etc.). - Keep PRs focused — one logical change per PR. Update
README.md/CHANGELOG.mdin the same PR when the change affects them. - ADRs are immutable once Accepted (
docs/adr/) — supersede with a new ADR rather than editing.
Ways of working
- Avoid breaking changes whenever avoidable. Prefer additive, backward-compatible changes. When a break is genuinely unavoidable, call it out explicitly (PR description +
CHANGELOG.md) and provide a migration path. - Develop behind feature flags. Gate new features — and any change to existing behaviour — behind a flag/config that is off by default, so it can ship dark, be rolled out incrementally, and be reverted without a code change. Remove the flag once the behaviour is the stable default.
More detail
- Contributing & conventions:
CONTRIBUTING.md - Release process:
RELEASING.md - Architecture decisions:
docs/adr/
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 · 42 lines · 474 tokens per session scan A 9b63b1838af7
ratel-local AGENTS.md is an instructions file published in the GitHub repository ratel-ai/ratel-local (13 stars, last pushed 2d ago), licensed MIT. It adds 474 tokens to every session, about $0.0024 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
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.
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).
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).
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.
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.