review

review is a command for Claude Code from AleksandarBisevac/claude-plugins. It costs 35 tokens per session (544 once invoked), scanned A, original, MIT.

A command for re-running the final checks for a completed phase of an audit pipeline. A phase is a defined group of project work, and sign-off includes review, tests, invariant checks, optional startup, and merging.

In plain words
What is it for?
It is for reviewing a phase again, running its test and consistency checks, optionally starting it, and merging it.
Why use it?
It provides a way to repeat the phase's approval checks after fixes or other changes.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the audit plugin — 2 skills, 20 commands, 4 agents, 4 hooks shipped together

Good fit It is for reviewing a phase again, running its test and consistency checks, optionally starting it, and merging it.

Compare 6 commands from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add AleksandarBisevac/claude-plugins
Claude Code
/plugin install audit

Made for: Claude Code.

Or install audit, the plugin that ships this one along with the rest of its 2 skills, 20 commands, 4 agents, 4 hooks.

Wrote 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.

agentmods badge for review

README.md
[![agentmods](https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/review/github.svg)](https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/review)
Your own site
<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.

agentmods 80×15 button for review

Your own site · 80×15
<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>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 544 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 5297e0cc408c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

plugins/audit/commands/review.md · 33 lines

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.

Changes

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.

  1. 2d ago Changed · +7 lines 5297e0cc408c
  2. 10d ago First seen · 26 lines · 35 tokens per session scan A 6933b9393bfd

Subscribe to this mod's changes

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.