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-plan)<a href="https://agentmods.dev/commands/karsten-s-nielsen/mad-scientist-skills/review-plan"><img src="https://agentmods.dev/badge/commands/karsten-s-nielsen/mad-scientist-skills/review-plan/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-plan"><img src="https://agentmods.dev/badge/commands/karsten-s-nielsen/mad-scientist-skills/review-plan.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 | $0.00009 | $0.00309 |
| Opus 5 | $0.00005 | $0.00154 |
| Sonnet 5 | $0.00002 | $0.00062 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
review-plan 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 an implementation plan you did not write.
Artifact: $ARGUMENTS
Use the unbiased-review skill. Read references/plan-review.md and
references/output-contract.md, plus references/tdd-rubric.md (check 2, test-first ordering, is
concrete in a plan) and references/stack-notes.md.
A plan is judged on whether someone else could execute it without re-deriving the spec's reasoning, and on whether each step can be verified when it is done.
Two things to establish before the rubric passes:
- Find the spec this plan implements, and check the plan against it in both directions — steps with no requirement, requirements with no step.
- Check
reviews/for a prior report on that spec. If a blocking finding was accepted and the plan faithfully implements the defective section anyway, that is a finding with a known ID, not a new one. Cite the ID.
Verify commit-structure claims rather than accepting them: a commit that deletes a consumer's only data source while its replacement arrives in the next commit is not independently valid, however it is described.
The skill's Hard rules apply — including rule 2: name the defect and what "resolved" looks like, never the patch.
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 · 31 lines · 9 tokens per session scan A 8ff144a4b818
review-plan is a command published in the GitHub repository karsten-s-nielsen/mad-scientist-skills (3 stars, last pushed 13d ago), licensed MIT. It adds 9 tokens to every session and 309 once invoked, about $0.0000 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
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.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
audit
Onboard an existing codebase: every domain's checks over the whole tree, then a triaged plan to bring it in line.
test
Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
sm-swab
Run slop-mop's iterative development loop for this repository.