Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add AleksandarBisevac/claude-plugins/plugin install auditWrote 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/aleksandarbisevac/claude-plugins/review)<a href="https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/review"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/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/commands/aleksandarbisevac/claude-plugins/review"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/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 | $0.00035 | $0.00544 |
| Opus 5 | $0.00017 | $0.00272 |
| Sonnet 5 | $0.00007 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00054 |
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 2d 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
/audit:review — re-run a phase's sign-off
$ARGUMENTS = the phase id. Read ${CLAUDE_PLUGIN_ROOT}/reference/orchestrator.md and
${CLAUDE_PLUGIN_ROOT}/reference/manifest-conventions.md first. Run the full preflight
(steps 1–5, including the lock) and emit Progress output (orchestrator) as you go.
Run Phase sign-off (orchestrator) for <phaseId> — use when tasks are already done and you
want to re-run the review / test gate / invariant check / runtime boot / merge (e.g. after applying
fixes). Then follow Reporting and release the lock.
The invariant check (sign-off step 3) reads the phase BRANCH. Re-running sign-off after the
branch was deleted is legitimate, and verify-invariants.py will answer no-basis for
branch-history rather than clean — read that as "the evidence is gone", not as a problem with
this run. meta.merge.deleteBranch is on by default, so on a phase that already landed this is
the normal outcome of a re-run, not a sign that something went wrong.
Re-running the landing step is safe and says so. close-phase.py asks the ancestry before it
writes anything, so a phase whose branch is already contained in its parent reports
already-contained, makes no git write at all, and exits 0. What a re-run WILL still do is the
cleanup the first run could not — a worktree that was dirty then and is clean now, or one the
first run was standing inside. Its --dry-run shows exactly that before you commit to it.
The reviewer is phase.reviewSkill ?? meta.areas[tag].reviewSkill ?? meta.reviewSkill — the
first level that is present answers, an explicit null is an answer (skip review; tests are
the signer), and with several area tags written order decides. /audit:status --phase <phaseId>
prints the resolved skill and the basis it came from; read that rather than re-deriving it.
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.
- 2d ago Changed · +7 lines 5297e0cc408c
- 10d ago First seen · 26 lines · 35 tokens per session scan A 6933b9393bfd
review is a command published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 544 once invoked, about $0.0002 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
octo-deliver
Delivery phase - Review, validate, and test with multi-AI quality assurance.
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.
test
Run the repository's actual test suite: every ecosystem's canonical runner — NOT run is never green.
v-collect
Re-run the collect + scope-gate + review tail of a Compound V run by run-id. Normalizes each job's output into results/ .json, re-runs the git-derived scope gate on every job, then the three-pass Review Gate (AC-gated). Use to re-check a dispatched run without re-dispatching workers.
ia-test-browser
Run browser tests on pages affected by current PR or branch.
ia-verify
Run pre-PR verification chain -- build, types, lint, tests, security scan, diff review.