Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file 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-optimize` skill 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, with `conftest.py` and `pytest.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**
…
The line at the top of this page pins the label git:20260926.35dafdd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_jdkrdl5nak5kkoxf
GET https://markdownregistry.com/api/v1/resolve?ref=karsten-s-nielsen/mad-scientist-skills/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/2b1f7087bb26c45e3ea260bcd2b6e6dfd114870a5a0af5637e0b5d6b0f8482f8
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
karsten-s-nielsen/mad-scientist-skills · plugins/mad-scientist-skills/skills/architecture-audit/SKILL.md · Comprehensive architecture audit with two modes and a single tier (beta). Planning mode evaluates architectural…
karsten-s-nielsen/mad-scientist-skills · plugins/mad-scientist-skills/skills/c4/SKILL.md · Creates interactive C4 model architecture diagrams using Structurizr DSL — the official C4 notation by Simon Brown…
karsten-s-nielsen/mad-scientist-skills · plugins/mad-scientist-skills/skills/cognitive-interface-audit/SKILL.md · Comprehensive cognitive interface audit with two modes and a single tier. Planning mode designs task models, user…
karsten-s-nielsen/mad-scientist-skills · plugins/mad-scientist-skills/skills/documentation-audit/SKILL.md · Comprehensive documentation audit with two modes and a single tier. Planning mode designs documentation strategy…
karsten-s-nielsen/mad-scientist-skills · plugins/mad-scientist-skills/skills/final-review/SKILL.md · Pre-commit quality gate — reviews all code and documentation for consistency, best practices, and completeness, then…
karsten-s-nielsen/mad-scientist-skills · plugins/mad-scientist-skills/skills/measure-before-optimize/SKILL.md · Pre-change measurement gate for perf-sensitive functions. Use BEFORE modifying any function that has a pytest-benchmark…
karsten-s-nielsen/mad-scientist-skills · plugins/mad-scientist-skills/skills/observability-audit/SKILL.md · Comprehensive observability audit with two modes and two tiers (beta). Planning mode designs telemetry strategy…
karsten-s-nielsen/mad-scientist-skills · plugins/mad-scientist-skills/skills/optimization-audit/SKILL.md · Comprehensive optimization audit with two modes and a single tier. Planning mode designs performance strategy, capacity…
karsten-s-nielsen/mad-scientist-skills · plugins/mad-scientist-skills/skills/research-discipline/SKILL.md · Use when designing or validating a quantitative metric, model, or ranking, when pre-registering an analysis, or before…
karsten-s-nielsen/mad-scientist-skills · plugins/mad-scientist-skills/skills/security-audit/SKILL.md · Comprehensive security audit with two modes and two tiers. Planning mode reviews architecture for security gaps (STRIDE…
karsten-s-nielsen/mad-scientist-skills · plugins/mad-scientist-skills/skills/unbiased-review/SKILL.md · Use when reviewing a spec, plan, or implementation produced by another session - verifies its claims against the actual…
