Borrowing it
Nothing to install: this file belongs to Lingtai-AI/lingtai. 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/Lingtai-AI/lingtai/main/CLAUDE.mdgit clone --depth 1 https://github.com/Lingtai-AI/lingtaiWrote 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/lingtai-ai/lingtai/claude-md)<a href="https://agentmods.dev/instructions/lingtai-ai/lingtai/claude-md"><img src="https://agentmods.dev/badge/instructions/lingtai-ai/lingtai/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/lingtai-ai/lingtai/claude-md"><img src="https://agentmods.dev/badge/instructions/lingtai-ai/lingtai/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 | $0.04562 | $0.04562 |
| Opus 5 | $0.02281 | $0.02281 |
| Sonnet 5 | $0.00912 | $0.00912 |
| Haiku 4.5 | $0.00456 | $0.00456 |
Grade A, and why
lingtai 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 10d 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 — 259 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.
Before any development work
Find and read this repository's local dev guide — the repository-root dev-guide-skill — before changing code, architecture documents, tests, or docs. It owns the workflow and routes each task through the exact baseline, the two distributed systems, focused validation, and the PR/side-effect gate without duplicating them:
- Where is the code and how is it connected? The distributed code-navigation system, rooted at
ANATOMY.md(descend intotui/ANATOMY.md/portal/ANATOMY.md). - What do interfaces and expected agent behavior promise? The distributed interface/Behavior system, rooted at
CONTRACT.md.
Read the dev guide first, then the paths it routes to, before editing.
Clarify human intent before coding
When a human gives conceptual, corrective, or ambiguous feedback — especially phrases like "stop and think," "you overcomplicated this," or corrections that map to multiple implementations:
- Pause coding. Restate the intended contract and wait for confirmation when scope is ambiguous.
- Classify findings. Label each concern: confirmed defect, edge risk, future refactor, or documentation/process issue. Do not treat all concerns as immediate code changes.
- Name the smallest change. Identify the minimal fix. Do not expand into a broader refactor because nearby code is related.
- No direct edits for self-initiated improvements. Self-initiated code changes go through issue → branch → PR → merge. Direct edits are for explicitly requested emergency fixes only. (The "Always work in a worktree" section below carves out single-line fixes and doc tweaks — those exceptions still apply.)
- Stop after stop. When a human says to stop coding, stop immediately. Switch to clarification or reporting only.
Always work in a worktree, never directly in the main checkout
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.
- 10d ago First seen · 259 lines · 4,562 tokens per session scan A 5d533ec03031
lingtai CLAUDE.md is an instructions file published in the GitHub repository Lingtai-AI/lingtai (670 stars, last pushed today), licensed Apache-2.0. It adds 4,562 tokens to every session, about $0.0228 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.