Borrowing it
Nothing to install: this file belongs to MingyiSecLab/Mingyi-Atlas. 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/MingyiSecLab/Mingyi-Atlas/main/CLAUDE.mdgit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/claude-md)<a href="https://agentmods.dev/instructions/mingyiseclab/mingyi-atlas/claude-md"><img src="https://agentmods.dev/badge/instructions/mingyiseclab/mingyi-atlas/claude-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/mingyiseclab/mingyi-atlas/claude-md"><img src="https://agentmods.dev/badge/instructions/mingyiseclab/mingyi-atlas/claude-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 | $0.02060 | $0.02060 |
| Opus 5 | $0.01030 | $0.01030 |
| Sonnet 5 | $0.00412 | $0.00412 |
| Haiku 4.5 | $0.00206 | $0.00206 |
Grade A, and why
Mingyi-Atlas 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 9d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project overview
Mingyi Atlas is a TypeScript/Node.js terminal AI agent for software engineering and authorized security assessment. It is published as @mingyilab/mingyi-atlas and exposes the mingyi-atlas CLI. The package is ESM-first, built with tsup, tested with Vitest, and requires Node.js >=22.13.0.
The product has two primary entry points:
src/main.ts— executable CLI entry. Starts the interactive TUI by default, routes--prompt/-pand--helpto headless mode, handles piped stdin, theme setup, analytics, cleanup, and fatal-error reporting.src/index.ts— programmatic factory.createMingyiAtlas()wires Mastra Harness, storage, auth, settings, model resolution, MCP, hooks, workspace, dynamic tools, subagents, observability, signals, and mode defaults.
Common commands
pnpm install # install dependencies
pnpm cli # run the CLI from source (tsx src/main.ts)
pnpm check # TypeScript typecheck (tsc --noEmit)
pnpm lint # ESLint
pnpm test # Vitest watch mode
pnpm test:run # run all unit tests once
pnpm build # build dist/ with tsup and copy built-in skills
pnpm pack:check # dry-run npm package contents
pnpm prepublishOnly # check + publish-sensitive tests + build
Run a single test file or area with Vitest directly:
pnpm vitest run src/agents/__tests__/prompts.test.ts
pnpm vitest run src/tools/__tests__/httpRequest.test.ts
pnpm vitest run src/agents/subagents/specialized
Useful focused test targets from the project docs:
pnpm vitest run src/agents/__tests__/tools.test.ts
pnpm vitest run src/agents/__tests__/builtin-skills.test.ts
pnpm vitest run src/agents/__tests__/build-skill-paths.test.ts
pnpm vitest run src/agents/subagents/specialized
For local CLI smoke checks:
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.
- 9d ago First seen · 157 lines · 2,060 tokens per session scan A 28619727af53
Mingyi-Atlas CLAUDE.md is an instructions file published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 2,060 tokens to every session, about $0.0103 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.
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.