Borrowing it
Nothing to install: this file belongs to kavo-labs/kavo. 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/kavo-labs/kavo/main/.claude/commands/review.mdgit clone --depth 1 https://github.com/kavo-labs/kavoWrote 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/kavo-labs/kavo/review)<a href="https://agentmods.dev/commands/kavo-labs/kavo/review"><img src="https://agentmods.dev/badge/commands/kavo-labs/kavo/review.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.01350 |
| Opus 5 | $0.00010 | $0.00675 |
| Sonnet 5 | $0.00004 | $0.00270 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Branch: !
git rev-parse --abbrev-ref HEAD - Working tree: !
git status --short - Committed-on-branch diff: !
git diff main...HEAD --stat - PR: !
gh pr view $ARGUMENTS --json number,title,state,isDraft,baseRefName,headRefName,url,mergeable 2>/dev/null || echo "NO PR"
Your task
Review $ARGUMENTS. This command covers two modes — pick one before doing anything else:
- Local mode: reviews uncommitted work still sitting in the working tree
(what
/implementleaves behind), before it gets committed. - PR mode: reviews a pushed, open pull request.
-
Pick the mode:
- If
$ARGUMENTSis a PR number, or no number was given but the context above shows an open PR for the current branch and the working tree is clean with nothing uncommitted beyond what that PR already contains, use PR mode. - Otherwise, if there is uncommitted work or a committed-but-unpushed diff on the current branch, use Local mode.
- If neither holds — clean tree, no PR, nothing on the branch — say so and stop. There is nothing to review.
- If
-
Get the code in front of you:
-
Local mode: the diff is already on disk. Don't assume
git diff main...HEADalone tells you what changed — uncommitted work doesn't show up there; usegit status --shortand the working tree directly. -
PR mode: if the PR's
headRefNameis not the currently checked-out branch, rungh pr checkout <n>to fetch and switch to it. Do not force-push, rebase, or amend anything on it. Diff it against its base, not blindly againstmain— a PR can target another branch:git diff <baseRefName>...<headRefName> --stat
-
-
Local mode only — format and gate:
pnpm prettifyLeave any resulting changes uncommitted —
/commitpicks them up along with everything else. Do not commit here.pnpm check pnpm docs:linksThat is build + typecheck +
depcruise+ the full test suite. If it fails, stop and report the failure output — do not proceed to review a change that doesn't build or pass its tests, and never weaken a test to make it pass.
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.
- 6d ago First seen · 117 lines · 21 tokens per session scan A 7170cc09f63b
review is a command published in the GitHub repository kavo-labs/kavo (12 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,350 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-02.
Other commands, from other repositories
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.