Borrowing it
Nothing to install: this file belongs to Raven-Scout/scout-plugin. 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/Raven-Scout/scout-plugin/main/CLAUDE.mdgit clone --depth 1 https://github.com/Raven-Scout/scout-pluginWrote 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/raven-scout/scout-plugin/claude-md)<a href="https://agentmods.dev/instructions/raven-scout/scout-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/raven-scout/scout-plugin/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 | $0.00721 | $0.00721 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
scout-plugin 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Working notes for AI agents in this repo (the Python Scout engine/plugin).
Fixtures must be anonymized — this repo and its two siblings are public
Scout runs against a real person's vault, so anything lifted from it into a
fixture or an inline test string must be scrubbed before it lands. All three
Scout repos — this one, Scout (desktop), and scout-iOS-app — are public.
- No real identifiers. Strip company/product names, real coworker names, real
Linear IDs, GitHub repos, and Slack workspaces/channels. Use the shared
stand-ins so fixtures stay internally consistent:
- People:
Alex/Priya/Sam; comment authoralex. - Linear:
PROJ-1234(neutral prefixes likeOPS-,DESK-for variety) — never the real team prefixes (AI-,KAI-,ST-, …). - GitHub:
example-org/<repo>. - Slack:
acme-co.slack.com/archives/C0123456789/p1700000000000000. - Vendors/products: a generic noun, not the brand.
- People:
- Anonymize content, not structure. Keep the tokens the parser is tested on
(synthetic
[#TAG]prefixes,**bold**,_(italic)_,[[wikilinks]],—separators,`code`). Only swap the words around them. - Don't hardcode personal config in source. The Linear deep-link workspace is
read from
SCOUT_LINEAR_WORKSPACE(defaultyour-workspace), not baked in; keep new connector/workspace specifics config- or env-driven the same way. - Preserve legitimate attribution — NOT leaks, leave them:
pyprojectauthors,.claude-plugin/marketplace.json/plugin.jsonowner,LICENSE, and the project's owngithub.com/<org>/…URLs (including the self-update URL).
parser-corpus.json is ONE byte-identical file living in three repos
engine/tests/fixtures/contract/parser-corpus.json is the canonical copy;
Scout (desktop) and scout-iOS-app vendor byte-identical copies, checksum-guarded
on both the Python and Swift sides — so you cannot edit just one copy. On any change
(anonymizing counts):
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 · 48 lines · 721 tokens per session scan A fe93692b8454
scout-plugin CLAUDE.md is an instructions file published in the GitHub repository Raven-Scout/scout-plugin (15 stars, last pushed yesterday), licensed MIT. It adds 721 tokens to every session, about $0.0036 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.
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.