agentmods.dev

review

review is a command for Claude Code from xzawed/claude-grok-build-plugin. It costs 13 tokens per session (406 once invoked), scanned A, original, MIT.

A review command that checks code changes produced by Grok, an AI coding assistant, before they are accepted.

In plain words
What is it for?
Use it after delegated coding work to inspect the diff and choose whether to accept it, revise it, send it back to Grok, or discard it.
Why use it?
It provides a manual quality gate for correctness, security, missing tests or documentation, and changes outside the requested scope.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grok plugin — 4 skills, 27 commands, 1 agent, 1 hook, 1 MCP server shipped together

not rated 1repo 2d ago A scan 13 tokens original MIT

Good fit Use it after delegated coding work to inspect the diff and choose whether to accept it, revise it, send it back to Grok, or discard it.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/xzawed/claude-grok-build-plugin/review
View source ↗ xzawed/claude-grok-build-plugin
Install

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.

Clone the repo
git clone --depth 1 https://github.com/xzawed/claude-grok-build-plugin

Made for: Claude Code.

Or install grok, the plugin that ships this one along with the rest of its 4 skills, 27 commands, 1 agent, 1 hook, 1 MCP server.

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/xzawed/claude-grok-build-plugin/review.svg)](https://agentmods.dev/commands/xzawed/claude-grok-build-plugin/review)
Your own site
<a href="https://agentmods.dev/commands/xzawed/claude-grok-build-plugin/review"><img src="https://agentmods.dev/badge/commands/xzawed/claude-grok-build-plugin/review.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 406 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 $0.00013 $0.00406
Opus 5 $0.00006 $0.00203
Sonnet 5 $0.00003 $0.00081
Haiku 4.5 $0.00001 $0.00041

Measured 8d ago against content hash e6fb55e4665a, 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 8d 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.

commands/review.md · 33 lines

What it actually says

Post-delegation quality gate. Use after grok_build_delegate / verify / resume (or when the user asks to review Grok's work).

Steps

  1. If you do not already have the last result, call grok_build_usage with project cwd and note recent[0] / lastSession / insights. Do not invent sessionIds.
  2. Inspect working tree diff for the files Grok touched (filesChanged from the tool result, or git status / git diff in the project). Prefer the listed paths; if worktree isolation was used, use grok_build_worktree diff/apply as needed.
  3. Check billing on the last Grok tool result:
    • SuperGrok / X Premium+ sessions should show billing: "subscription".
    • Unexpected metered_api → the server is running with GROK_BUILD_AUTH_MODE=api; that setting alone decides the tag (subscription mode strips the API-key vars before spawn).
  4. Adversarial review (Claude owns this — do not re-delegate the review itself):
    • Correctness vs the original task
    • Security / secrets / dangerous defaults
    • Tests or docs left incomplete
    • Scope creep outside the request
  5. Present a short verdict: accept / fix-with-Claude / fix-with-Grok (/grok:resume) / discard (worktree remove if isolated).
  6. Never commit or open a PR unless the user explicitly asks after the review.

Do not

  • Auto-commit, auto-PR, or force-push
  • Call Grok for HIGH-risk security/architecture final judgment without user intent
  • Skip showing filesChanged / billing when available
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. 8d ago First seen · 33 lines · 13 tokens per session scan A e6fb55e4665a

Subscribe to this mod's changes

review is a command published in the GitHub repository xzawed/claude-grok-build-plugin (1 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 406 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 2026-08-31.

Claude CodeCode reviewai-coding-assistantclaude-code-plugindeveloper-toolsgrokmcp
Related

Other commands, from other repositories

merge

Finish a PR properly: every check green, every review addressed — human and bot — then merge and clean up.

azrtydxb/procoder · 23 tokens

pr

Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.

azrtydxb/procoder · 20 tokens

spec

Spec-first design: a gap-closing interview that produces a complete spec, with a quality controller that blocks until every section is answered and every question resolved.

azrtydxb/procoder · 31 tokens

copilot-leak

Copilot's auto-review escapes: find them since the last look, sanitise them, and turn each one into a lesson.

azrtydxb/procoder · 26 tokens

debug

Systematic debugging: root cause before any fix, one hypothesis at a time, and a three-strikes rule that questions the architecture instead of stacking patches.

azrtydxb/procoder · 31 tokens

docs

The documentation report: references, diagrams, drift, API docs, badges, README structure, links, Pages.

azrtydxb/procoder · 22 tokens