Borrowing it
Nothing to install: this file belongs to corveil/crow. 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/corveil/crow/main/CLAUDE.mdgit clone --depth 1 https://github.com/corveil/crowWrote 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/corveil/crow/claude-md)<a href="https://agentmods.dev/instructions/corveil/crow/claude-md"><img src="https://agentmods.dev/badge/instructions/corveil/crow/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/corveil/crow/claude-md"><img src="https://agentmods.dev/badge/instructions/corveil/crow/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 | $0.14842 | $0.14842 |
| Opus 5.5 | $0.05937 | $0.05937 |
| Sonnet 5.5 | $0.02968 | $0.02968 |
| Haiku 4.5 | $0.01484 | $0.01484 |
Grade A, and why
crow 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 today.
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 — 577 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crow — Manager Context
This is the development root managed by Crow. The Manager tab runs Claude Code here to orchestrate work sessions via the crow CLI.
Naming this Manager session
Additional Managers are created as Manager 2, Manager 3, … — a title that tells the operator nothing about the work. As soon as you know what this session is for, give it a name that reflects that, so the sidebar stays legible.
On the first real ask of this session — the first user turn that hands you actual work, not a greeting — and before you start that work:
- If
$CROW_SESSION_IDis00000000-0000-0000-0000-000000000000, you are the primary Manager. Never rename it — stop here. - Run
crow get-session --session "$CROW_SESSION_ID"and readname. If it is not of the formManager <N>(e.g.Manager 2), this session was already named — stop here. - Otherwise derive a short title from the ask: 2–6 words or a short slug (
ios-keyboard-cursor,review crow-1078,file keyboard bug). It must be non-empty, ≤256 characters, free of control characters, and must not collide with an existing name — checkcrow list-sessions. - Rename through the CLI, so the persist / sidebar row / agent
/rename(CROW-629) all run on one path:crow rename-session --session "$CROW_SESSION_ID" "<derived-name>"
Do this once. After step 4 the name is no longer Manager <N>, so step 2 keeps it from firing again on later turns. Never rename on every message, and never rename the primary Manager or a session the operator already named.
Architecture Decision Records
Architectural decisions live in docs/adr/. Read docs/adr/README.md for the index, and copy docs/adr/template.md to start a new one. When superseding a decision, update the old ADR's Status field to Superseded by NNNN — don't delete it. The history is the point.
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.
- today Changed · +4 lines · +152 tokens per session 08a8c3b043ee
- yesterday Changed · +5 lines · +635 tokens per session 555b30202bf8
- 2d ago Changed · +1 lines · +28 tokens per session c9aeab3c5140
- 3d ago Changed · +4 lines · +198 tokens per session 37c6e9c62ba4
- 12d ago Changed · +1 lines · +191 tokens per session c32322cce6a5
- 13d ago Changed · +21 lines · +451 tokens per session 6a68fa16b117
- 15d ago Changed · +77 tokens per session 24a8b20b5553
- 16d ago Changed · +2 lines · +67 tokens per session ac3ba27cbe54
- 28d ago Changed · +2 lines · +69 tokens per session e9fb6956eb16
- 29d ago First seen · 537 lines · 12,974 tokens per session scan A aa6f6ea442f0
crow CLAUDE.md is an instructions file published in the GitHub repository corveil/crow (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 14,842 tokens to every session, about $0.0594 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.