Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git 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/commands/karsten-s-nielsen/mad-scientist-skills/review-spec)<a href="https://agentmods.dev/commands/karsten-s-nielsen/mad-scientist-skills/review-spec"><img src="https://agentmods.dev/badge/commands/karsten-s-nielsen/mad-scientist-skills/review-spec/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/commands/karsten-s-nielsen/mad-scientist-skills/review-spec"><img src="https://agentmods.dev/badge/commands/karsten-s-nielsen/mad-scientist-skills/review-spec.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 | $0.00011 | $0.00311 |
| Opus 5 | $0.00005 | $0.00156 |
| Sonnet 5 | $0.00002 | $0.00062 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
review-spec 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 12d 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
Review a spec / design doc you did not write.
Artifact: $ARGUMENTS
Use the unbiased-review skill. Read references/spec-review.md and
references/output-contract.md; add references/tdd-rubric.md and
references/hexagonal-rubric.md if the spec makes claims about tests or architecture, and
references/stack-notes.md for the platform specifics involved.
Run all six phases in order. Do not skip Phase 1 — enumerate every checkable claim before judging any
of them, because a spec's file:line references, counts, and measurements are the parts specific
enough to be wrong, and a wrong one propagates into every plan and commit built on it.
If the argument is a path, the target repo is its enclosing git repo: pin HEAD, git status --short
and the artifact's sha256 before reading, so a later round can compute what changed. If the spec was
pasted rather than pointed at, say so in the report — the comparison is text-only and that limits what
Phase 2 can verify.
The skill's Hard rules apply. In particular: nothing is written to the target, BLOCKING
requires a named consequence of shipping, and Could not verify is mandatory.
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.
- 12d ago First seen · 26 lines · 11 tokens per session scan A ef914f1cddf7
review-spec is a command published in the GitHub repository karsten-s-nielsen/mad-scientist-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 11 tokens to every session and 311 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
merge
Finish a PR properly: every check green, every review addressed — human and bot — then merge and clean up.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
spec
Spec-first design: a gap-closing interview that produces a complete spec, with a quality controller that blocks until every section is answered and every question resolved.
debug
Systematic debugging: root cause before any fix, one hypothesis at a time, and a three-strikes rule that questions the architecture instead of stacking patches.
plan
Turn an approved spec into an implementation plan an engineer with zero context could execute — with a quality controller that blocks placeholders and hollow tasks.
tdd
Test-driven development with tests that actually catch breaks: red before green, name the break each test catches, and the mutation check before done.