Borrowing it
Nothing to install: this file belongs to racecraft-lab/racecraft-plugins-public. 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/racecraft-lab/racecraft-plugins-public/main/AGENTS.mdgit clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWrote 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/racecraft-lab/racecraft-plugins-public/agents-md)<a href="https://agentmods.dev/instructions/racecraft-lab/racecraft-plugins-public/agents-md"><img src="https://agentmods.dev/badge/instructions/racecraft-lab/racecraft-plugins-public/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 | $0.01889 | $0.01889 |
| Opus 5 | $0.00945 | $0.00945 |
| Sonnet 5 | $0.00378 | $0.00378 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
racecraft-plugins-public 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 3d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Agent Instructions
Use this file as the shared agent contract for Codex, Claude Code, Gemini, and Copilot. Keep it concise: agent context should contain durable behavior, not release history, workflow runbooks, generated-plan exhaust, or long plugin internals.
Working Rules
These rules are adapted from Andrej Karpathy's agent guidance and this repo's own failure patterns.
1. Surface assumptions before editing
- State assumptions in chat before touching files.
- If a manifest, release, CI, or generated-artifact change is ambiguous, ask.
- If a simpler path might solve the request, name it before doing larger work.
- Stop and describe confusion instead of pushing through on a guess.
2. Make the simplest change that solves the task
- Do not add features, flags, abstractions, or helper layers for hypothetical future callers.
- Prefer existing repo patterns and source-of-truth files over new conventions.
- If a change feels larger than the request, shrink it or explain why the size is necessary.
3. Keep edits surgical
- Touch only files that directly serve the request.
- Do not reformat adjacent JSON, reorder manifest keys, or clean up unrelated comments.
- Remove only code or prose that your change actually orphans.
- Match local style even when you would normally write it differently.
4. Verify success explicitly
- Decide the relevant check before coding.
- Prefer the smallest useful check while iterating, then run the broader gate when the changed surface warrants it.
- Before creating a PR or marking it ready, validate the exact final title with
the repository release-readiness gate. The live gate requires
<type>(<lowercase-scope>): <plain English description>. - If verification cannot run, report the exact command and reason.
Repository Orientation
- This is a public Claude Code and Codex plugin marketplace.
- Current plugin source lives under
speckit-pro/. - Repository-only validation lives under
tests/speckit-pro/. - The docs site lives under
docs-site/. - Historical specs and generated planning artifacts are context on demand, not always-on agent 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.
- 3d ago Changed · +2 lines · +50 tokens per session 9f61686a2617
- 7d ago First seen · 175 lines · 1,839 tokens per session scan A c74a4dcf18e4
racecraft-plugins-public AGENTS.md is an instructions file published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed today), licensed MIT. It adds 1,889 tokens to every session, about $0.0094 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.