review

review is a command for Claude Code from artemnovichkov/skills. It costs 23 tokens per session (528 once invoked), scanned A, original, MIT.

A review command that creates or uses a REVIEW.md policy, then checks the current code change against it. The policy covers bugs, security, requirements, and project principles.

In plain words
What is it for?
Use it to review a change against its specification and implementation plan, while excluding generated or vendored code and checks already handled by continuous integration.
Why use it?
It makes reviews consistent and keeps people from spending review time on repeated formatting or naming comments.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

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 sdlc plugin — 1 skill, 8 commands, 1 agent, 1 hook shipped together

Good fit Use it to review a change against its specification and implementation plan, while excluding generated or vendored code and checks already handled by continuous integration.

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 artemnovichkov/skills
Claude Code
/plugin install sdlc

Made for: Claude Code.

Or install sdlc, the plugin that ships this one along with the rest of its 1 skill, 8 commands, 1 agent, 1 hook.

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/artemnovichkov/skills/review/github.svg)](https://agentmods.dev/commands/artemnovichkov/skills/review)
Your own site
<a href="https://agentmods.dev/commands/artemnovichkov/skills/review"><img src="https://agentmods.dev/badge/commands/artemnovichkov/skills/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/artemnovichkov/skills/review"><img src="https://agentmods.dev/badge/commands/artemnovichkov/skills/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 528 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 $0.00023 $0.00528
Opus 5 $0.00012 $0.00264
Sonnet 5 $0.00005 $0.00106
Haiku 4.5 $0.00002 $0.00053

Measured yesterday against content hash 1ff2239edb08, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 yesterday.

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.

skills/sdlc/commands/review.md · 40 lines

What it actually says

Stage 5 — Review the same way every time

Every change gets the same passes, so human attention can go to intent and risk instead of to naming and formatting.

Workflow

1. Ensure a review policy exists

If REVIEW.md is absent, draft it from ${CLAUDE_PLUGIN_ROOT}/templates/REVIEW.md, adapted to this repo:

  • Passes: bugs and logic errors; security and vulnerabilities; compliance with the spec, the plan, and the repo's stated principles.
  • Important vs Nit: define the line explicitly. Style and naming are nits. Cap the number of nits reported.
  • Exclusions: generated paths, vendored code, and anything CI already enforces — commenting on those wastes the review.

Show it to the user for correction and offer the commit. REVIEW.md is policy: it is worth arguing over once so it does not have to be argued in every PR.

2. Run the review

Reuse the existing reviewer rather than writing another one:

  • If the code-review plugin is installed, run /code-review and pass REVIEW.md as the policy the review must apply, along with sdlc/spec/<slug>.md and sdlc/plan/<slug>.md for the compliance pass.
  • Otherwise, review the diff yourself against each REVIEW.md pass in turn, one pass at a time. Report findings ranked by severity, and drop anything that is only style.

The compliance pass is the one a generic reviewer cannot do: does the diff actually implement the accepted spec, and does it match the accepted plan? Name the divergences.

3. Close the loop

  • Any finding that is a repeat of an earlier correction goes into CLAUDE.md — that is what stops it recurring.
  • If the diff departs from the plan, update sdlc/plan/<slug>.md.
  • For a GitHub PR, the user can tag @claude on review comments to have them addressed on the branch.

4. Boundary

You do not approve your own work. Present findings and let the user decide what merges. If asked to merge, say plainly that the merge decision is theirs and wait for an explicit go-ahead.

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. yesterday First seen · 40 lines · 23 tokens per session scan A 1ff2239edb08

Subscribe to this mod's changes

review is a command published in the GitHub repository artemnovichkov/skills (36 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 528 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 2026-09-07.