Borrowing it
Nothing to install: this file belongs to karsten-s-nielsen/mad-scientist-skills. 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/karsten-s-nielsen/mad-scientist-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/karsten-s-nielsen/mad-scientist-skillsWrote 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/karsten-s-nielsen/mad-scientist-skills/agents-md)<a href="https://agentmods.dev/instructions/karsten-s-nielsen/mad-scientist-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/karsten-s-nielsen/mad-scientist-skills/agents-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/karsten-s-nielsen/mad-scientist-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/karsten-s-nielsen/mad-scientist-skills/agents-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 | $0.00466 | $0.00466 |
| Opus 5.5 | $0.00186 | $0.00186 |
| Sonnet 5.5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
mad-scientist-skills AGENTS.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 1mo 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
AGENTS.md — Contributor guide for mad-scientist-skills
This is a Claude Code plugin repo: skills and slash commands under
plugins/mad-scientist-skills/. It ships no package — there is no
pyproject.toml or package.json. This file is the always-loaded contributor
brief; long-form docs live in README.md, CONTRIBUTING.md, and docs/.
Before you change anything
- Pre-change discipline (ADR-001): run the relevant pre-change gate before
editing perf- or contract-sensitive code (for example the
measure-before-optimizeskill before touching a benchmarked function). - Chesterton's Fence: understand why a guard, rule, or convention exists before you remove it.
Tests
- Tests live outside the skill directories (ADR-002), under
tests/:tests/skills/**plus root-level guards, withconftest.pyandpytest.ini. - Run the full suite before declaring work done:
python -m pytest. - New tests are stdlib-only where practical and read files with
encoding="utf-8".
Audit skills read both instruction files
Skills that read a consumer repo's project instructions must read both
CLAUDE.md and AGENTS.md, never one alone. A migrated repo's CLAUDE.md is a
one-line @AGENTS.md shim, so the real rules live in AGENTS.md; an unmigrated
repo may still keep a real CLAUDE.md. tests/test_agents_md_awareness.py
enforces this pairing across the shipped skills.
Committing
- Do the work on one feature branch off
main— never a worktree. - One fully-tested, coherent commit per change; no micro-commits.
- Run
/final-reviewbefore committing — it regeneratesarchitecture.htmlvia Graphvizdot(never PlantUML Smetana). commit,push, opening thePR, andmergeare separate actions; each waits for explicit maintainer approval.
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.
- 1mo ago First seen · 40 lines · 466 tokens per session scan A 2b1f7087bb26
mad-scientist-skills AGENTS.md is an instructions file published in the GitHub repository karsten-s-nielsen/mad-scientist-skills (3 stars, last pushed 26d ago), licensed MIT. It adds 466 tokens to every session, about $0.0019 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 2026-09-27.
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.