Borrowing it
Nothing to install: this file belongs to chenxin-yan/crust. 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/chenxin-yan/crust/main/AGENTS.mdgit clone --depth 1 https://github.com/chenxin-yan/crustWrote 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/chenxin-yan/crust/agents-md)<a href="https://agentmods.dev/instructions/chenxin-yan/crust/agents-md"><img src="https://agentmods.dev/badge/instructions/chenxin-yan/crust/agents-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/chenxin-yan/crust/agents-md"><img src="https://agentmods.dev/badge/instructions/chenxin-yan/crust/agents-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 | $0.00327 | $0.00327 |
| Opus 5.5 | $0.00131 | $0.00131 |
| Sonnet 5.5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
crust 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 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.
What it actually says
Tests
- Vitest via Vite+:
import { describe, expect, it, beforeEach, afterEach, vi } from "vite-plus/test";pnpm run testfrom the root,pnpm exec vp test run [file]in a package. - Tests run on Node. Exercise Bun-only behavior (
Bun.build, compile, PTY) by spawningbunas a subprocess with an explicit timeout. - Unit tests: co-located (
src/foo.test.tsbesidesrc/foo.ts) - Compile-only type tests: co-located
src/foo.test-d.ts; enforced bypnpm run check:types(tsc), not collected byvp test. - Integration/smoke tests: package-local
packages/<pkg>/tests/
Documentation
Update relevant docs/code comments in the same change as the code. Stale docs = bug.
Doc surfaces:
apps/docs/content/docs/guide/*.mdx— conceptual guidesapps/docs/content/docs/modules/*.mdx— per-package referenceapps/docs/content/docs/api/*.mdx— public API reference
Before submitting:
- Examples in changed docs compile against the new API
- Cross-links resolve;
meta.jsonupdated if pages added/removed/reordered
Changesets
Do not edit CHANGELOG.md manually. Run pnpm run changeset to record user-visible changes; release tooling consumes them. Skip changesets for changes with no end-user behavior impact (internal refactors, tests, docs, CI, tooling).
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 Changed · +1 lines · +70 tokens per session 10aab4c5af9b
- 1mo ago Changed · -17 tokens per session 140facc88d84
- 1mo ago Changed · -14 lines · -128 tokens per session f36e703f25c7
- 1mo ago Changed · +28 tokens per session f6451f8ec4ae
- 1mo ago Changed · -1 lines · -14 tokens per session a96a90fd5dae
- 2mo ago First seen · 41 lines · 388 tokens per session scan A ef69ce63a01f
crust AGENTS.md is an instructions file published in the GitHub repository chenxin-yan/crust (414 stars, last pushed 7d ago), licensed MIT. It adds 327 tokens to every session, about $0.0013 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
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.