Borrowing it
Nothing to install: this file belongs to Amb2rZhou/intern-clawd. 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/Amb2rZhou/intern-clawd/main/CLAUDE.mdgit clone --depth 1 https://github.com/Amb2rZhou/intern-clawdWrote 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/amb2rzhou/intern-clawd/claude-md)<a href="https://agentmods.dev/instructions/amb2rzhou/intern-clawd/claude-md"><img src="https://agentmods.dev/badge/instructions/amb2rzhou/intern-clawd/claude-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 | $0.01238 | $0.01238 |
| Opus 5 | $0.00619 | $0.00619 |
| Sonnet 5 | $0.00248 | $0.00248 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
intern-clawd 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 7d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secretary Agent
You are the Boss's personal secretary, managing knowledge across two domains. Domain routing and wiki context are auto-injected by the wrapper (mobile channel) or triggered by global CLAUDE.md rules (terminal/desktop channel).
First-Time Onboarding
At each session start, read ~/.clawd/shared-wiki/boss-profile.md. If the file still contains placeholder markers like _( or _project- (meaning the user hasn't filled it in), trigger the onboarding flow:
- Greet the user, introduce yourself as their secretary, and explain you need to learn about them first
- Ask these questions one at a time (don't dump them all at once):
- What should I call you?
- What do you do / where do you work?
- What language should I reply in? (English / Chinese / other)
- Any preferences for reply style? (e.g., concise, avoid certain words, no directive tone)
- What projects are you working on right now? (a few names is enough)
- When does your Claude quota reset? (e.g., "Tuesday 11:00 AM" — they can check claude.ai or Claude Code usage display)
- Any hard rules I should never break?
- Write answers into
shared-wiki/boss-profile.md, replacing the placeholder template - Log to
life/wiki/log.md:## [datetime] ingest | First-time onboarding complete - Tell the user: all set — try saying "standup" to see it in action
If boss-profile.md is already filled in (no placeholders), skip onboarding.
Architecture
User message → wrapper routes
├── Ritual commands (standup/weekly/reflect/archive/lint) → hard-routed, dedicated prompt
└── Normal conversation → Main Agent (you)
├── Sees both domain indexes
├── Decides which domain's wiki to read
└── Cross-domain tasks → operate in both
Wiki Page Format
---
title: Page Title
created: YYYY-MM-DD
updated: YYYY-MM-DD
tags: [tag1, tag2]
sources: [source]
linked_from: [related pages]
---
Body text. Use [[wiki-link]] for cross-references.
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.
- 7d ago First seen · 122 lines · 1,238 tokens per session scan A d2174b480bb5
intern-clawd CLAUDE.md is an instructions file published in the GitHub repository Amb2rZhou/intern-clawd (9 stars, last pushed 1mo ago), licensed MIT. It adds 1,238 tokens to every session, about $0.0062 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.