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.
npx skills add mrclrchtr/supi --skill code-reviewgit clone --depth 1 https://github.com/mrclrchtr/supiWrote 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/skills/mrclrchtr/supi/code-review)<a href="https://agentmods.dev/skills/mrclrchtr/supi/code-review"><img src="https://agentmods.dev/badge/skills/mrclrchtr/supi/code-review/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/skills/mrclrchtr/supi/code-review"><img src="https://agentmods.dev/badge/skills/mrclrchtr/supi/code-review.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 | $0.00044 | $0.01054 |
| Opus 5.5 | $0.00018 | $0.00422 |
| Sonnet 5.5 | $0.00009 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
code-review 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.
This is a copy
83% identical to code-review — 121 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code review
Use review_run for this workflow. It freezes one Review Target and runs the Standards and Spec tasks independently. Keep their results separate. If review_run is unavailable, report that this workflow is unavailable. Do not replace it with agent_run or generic agents.
Process
1. Resolve the Review Target
Identify the before and after states once.
- For committed changes since a branch or tag, resolve the merge base with
git merge-base <fixed-point> HEAD. Pass that full commit ascommitted.fromand passHEADascommitted.to. - If the user gives two exact endpoints, resolve each endpoint and pass them as
committed.fromandcommitted.to. - To include staged, unstaged, or non-ignored untracked files, use
workingTree.from. Use the merge base for branch work, orHEADfor work-in-progress changes only. - For a state audit, use
mode: "state"and omitfrom.
Review endpoints must resolve to commits. Do not pass Git range syntax to review_run. If the request is not a state audit or a work-in-progress review and no fixed point is available, ask for one.
2. Identify the Spec source
Search in this order:
- Issue references in commit messages. Use the repository issue workflow when one exists.
- A path or issue that the user supplied.
- A specification under
docs/,specs/, or.scratch/that matches the branch or change. - Ask the user when no source is available. If the user confirms that there is no Spec, omit the Spec task and state this in the report.
Record each authoritative source as a criteriaSources item with a useful summary.
3. Identify the Standards sources
Find repository instruction files, contribution guides, coding standards, and relevant package-local guidance. Reviewers do not receive ambient context files. Put each necessary rule in the task instructions or identify its repository file in criteriaSources.
Apply this smell baseline as advisory criteria. A documented repository rule overrides it. Report each match as a judgment, not as a hard violation. Skip checks that automated tooling already enforces.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -12 lines · -50 tokens per session 268688b878fe
- 1mo ago First seen · 101 lines · 94 tokens per session scan A 3fd8adf8938f
code-review is a skill published in the GitHub repository mrclrchtr/supi (102 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,054 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 83% identical to code-review, differing in 121 lines, and is treated as a copy.
Other skills, from other repositories
muse-delegate
Delegate a coding task to Muse Code (muse) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Muse — phrasings like "have Muse do X", "delegate this to Muse", "run it through Muse", or "use Muse to implement/fix/refactor" — or wants…
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
review
Review a change for correctness, security, and missing tests.
pi-parity-review
Adversarially verify that a ported change is faithful to the original pi implementation (TS source + published npm build). Use after porting upstream pi changes, or standalone on any area of this repo ("is X faithful to pi?").
pi-go-review
Review ported Go code for idiomatic quality — that the port maximizes Go rather than transliterating TypeScript. Use after porting upstream pi changes, or standalone on any diff in this repo.
review-pr
Deeply review a GitHub pull request.