claude-review

claude-review is a skill for Codex from Beaulewis1977/claude-plugin-for-codex. It costs 36 tokens per session (403 once invoked), scanned A, original, MIT.

A read-only code review that asks Claude to examine current uncommitted changes or a chosen Git base revision and report findings with file and line locations.

In plain words
What is it for?
Use it to review a defined change set, order findings by severity, and separate concrete issues from remaining risks and open questions.
Why use it?
It gives you an independent review of risks and defects without changing the code or silently applying fixes.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to review a defined change set, order findings by severity, and separate concrete issues from remaining risks and open questions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/beaulewis1977/claude-plugin-for-codex/claude-review
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.

Any agent
npx skills add Beaulewis1977/claude-plugin-for-codex --skill claude-review
Clone the repo
git clone --depth 1 https://github.com/Beaulewis1977/claude-plugin-for-codex

Made for: Codex.

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 claude-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/beaulewis1977/claude-plugin-for-codex/claude-review/github.svg)](https://agentmods.dev/skills/beaulewis1977/claude-plugin-for-codex/claude-review)
Your own site
<a href="https://agentmods.dev/skills/beaulewis1977/claude-plugin-for-codex/claude-review"><img src="https://agentmods.dev/badge/skills/beaulewis1977/claude-plugin-for-codex/claude-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 claude-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/beaulewis1977/claude-plugin-for-codex/claude-review"><img src="https://agentmods.dev/badge/skills/beaulewis1977/claude-plugin-for-codex/claude-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 403 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 $0.00036 $0.00403
Opus 5 $0.00018 $0.00201
Sonnet 5 $0.00007 $0.00081
Haiku 4.5 $0.00004 $0.00040

Measured 12d ago against content hash e434bab670f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

claude-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 12d 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/claude-code/skills/claude-review/SKILL.md · 39 lines

What it actually says

Claude Review

Ask Claude to review a defined change set without fixing it.

Target and output

Default to all current uncommitted changes, including staged, unstaged, and untracked work. When the user specifies a base ref, pass it with --base. Request actionable findings ordered by severity with file:line locations, then separate residual risks and open questions. Never silently fix or apply a finding.

Workflow

  1. Resolve <plugin-root>/scripts/claude-companion.mjs to an absolute path.
  2. Make exactly one runtime invocation. Runtime action: review.
  3. Classify routine or bounded review as normal, substantial review as hard, and the most complex or high-stakes review as very-hard. Pass the classification with --tier; explicit model and effort selections always win. Pass --cwd with the current workspace and --json as separate arguments, plus base, background, timeout, or session flags only when selected.
  4. Write any free-form review task and context to stdin. Never place task text in an option, argument, or shell command. Use an argument array; never concatenate or interpolate values into a shell command. Use the execution tool's separate stdin channel; if it exposes an interactive process session, send the text there and explicitly close stdin before waiting.
  5. Keep this read-only. The runtime forces plan permission and safe-mode. Never edit, write, fix, or apply changes, and do not request bypass permissions.
  6. Attribute Claude's findings, verify them against the code, and report disagreements or uncertainty. Do not duplicate the review with another Claude run.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 39 lines · 36 tokens per session scan A e434bab670f1

Subscribe to this mod's changes

claude-review is a skill published in the GitHub repository Beaulewis1977/claude-plugin-for-codex (3 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 403 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.