Borrowing it
Nothing to install: this file belongs to shmulc8/captain-obvious. 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/shmulc8/captain-obvious/main/CLAUDE.mdgit clone --depth 1 https://github.com/shmulc8/captain-obviousWrote 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/shmulc8/captain-obvious/claude-md)<a href="https://agentmods.dev/instructions/shmulc8/captain-obvious/claude-md"><img src="https://agentmods.dev/badge/instructions/shmulc8/captain-obvious/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/shmulc8/captain-obvious/claude-md"><img src="https://agentmods.dev/badge/instructions/shmulc8/captain-obvious/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 | $0.00413 | $0.00413 |
| Opus 5.5 | $0.00165 | $0.00165 |
| Sonnet 5.5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
captain-obvious 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 2mo 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.
What it actually says
captain-obvious — contributor notes
- Run the self-tests:
npm install typescript@^5 --no-save --no-audit --no-fundonce, thenpython3 -m unittest discover -v tests. The tests are unittest TestCase classes with pytest-style filenames — plainpytestalso works, but CI runs unittest discover; keep new tests compatible with it (no pytest fixtures/parametrize). - TS tests skip silently when
typescriptis not installed at the repo root. A fully green run must show zeroskippedlines. - Parity rule: the Python (
skills/captain-obvious/scripts/co_py/) and TypeScript (.../co_ts/) engines implement the same detector catalog. A detector change lands on BOTH sides (analyzer.py + analyzer.mjs / classifier.mjs) plus a row inreferences/detectors.mdand the README table, or states in the PR why it is language-specific. - Zero dependencies, on purpose: the Python scripts are stdlib-only; the
Node scripts import nothing but
node:*and the TARGET repo's owntypescript. The skill must run when copied bare into~/.claude/skills/. Never add a manifest dependency toskills/. - Finding contract: every finding is
{file, line, test, category, level: proven|advisory, deletable: safe|aggressive|report-only, reason}. Onlyproven+deletable: safeis auto-deleted by--fix— treat any change that widens that set as high-risk and test it intests/. - Write-time hook:
hooks/prevent.py, off by default; enable withCAPTAIN_OBVIOUS_HOOK=block|warn. It must always fail open.
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.
- 2mo ago First seen · 25 lines · 413 tokens per session scan A 20d2985be751
captain-obvious CLAUDE.md is an instructions file published in the GitHub repository shmulc8/captain-obvious (15 stars, last pushed 29d ago), licensed MIT. It adds 413 tokens to every session, about $0.0017 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.