A review that compares an implementation with its approved plan. It uses the plan and the final code changes to identify requirements that were missed or changed.

Use it before opening a pull request or finishing work to find differences from the plan and decide which follow-up changes are justified.

It gives a fresh check for scope drift that can be easy to overlook while working inside the implementation.

plan:review — Skill for Claude Code by bendrucker/claude

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 bendrucker/claude --skill review

Clone the repo

git clone --depth 1 https://github.com/bendrucker/claude

Made for: Claude Code.

Or install plan, the plugin that ships this one along with the rest of its 1 skill.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bendrucker/claude/review/github.svg)](https://agentmods.dev/skills/bendrucker/claude/review)

Your own site

<a href="https://agentmods.dev/skills/bendrucker/claude/review"><img src="https://agentmods.dev/badge/skills/bendrucker/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bendrucker/claude/review"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 373 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.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.00373
Opus 5.5	$0.00018	$0.00149
Sonnet 5.5	$0.00009	$0.00075
Haiku 4.5	$0.00005	$0.00037

Measured 10d ago against content hash f48baa293deb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

plan: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 10d 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/plan/skills/review/SKILL.md · 28 lines

What it actually says

Plan Review

Compare the implementation against the approved plan through a reviewer that sees only the plan and the diff. Relay where the implementation drifted and what follow-ups that warrants.

Fork the Review

The approved plan is the file under ~/.claude/plans/ whose path was injected into this session when plan mode exited. With no injected path, there is no approved plan: say so and stop.

Dispatch a background Agent: analyst when your agent types list it, otherwise general-purpose. Spawn a fresh agent rather than a fork. The reviewer starts without this session's context. Use a cheaper model when one is set. Hand it absolute paths to the plan file and to the rubric references/divergence.md, resolved against this skill's base directory. Tell it to:

read the plan file.
diff the implementation against the branch's base. The open PR's base is authoritative (gh pr view --json baseRefName -q .baseRefName). With no PR, use the repository default (gh repo view --json defaultBranchRef -q .defaultBranchRef.name). A stacked branch targets its parent. Include uncommitted work: git diff <base>...HEAD, plus git diff HEAD and git status --short.
return the report the rubric defines.

Report

Relay the agent's report verbatim: divergences with their classification, requirements drift, ranked follow-ups split fix-before-merge from later, and the verdict.

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.

references/divergence.md 1.6 KB

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.

10d ago Changed · -4 lines f48baa293deb
2mo ago First seen · 32 lines · 46 tokens per session scan A d1ab3932c278

Subscribe to this mod's changes

plan:review is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 373 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.

Claude Code Code review Planning claude-code-plugin

plan:review next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
plan:reviewbendrucker/claude	Skill	18	today	MIT	A	46	Claude Code
reviewSethGammon/Citadel	Skill	928	4d ago	MIT	A	17	Claude Code
critical-code-reviewerposit-dev/skills	Skill	561	7d ago	MIT	A	67	Claude Code
brooks-sweephyhmrright/brooks-lint	Skill	1.6k	today	MIT	A	178	Claude Code
pr-reviewnitinjain999/platform-skills	Skill	71	yesterday	Apache-2.0	A	81	Claude Code
skill-distilleriliaal/whetstone	Skill	36	today	MIT	A	91	Claude Code
review-depthjszmajda/lid	Skill	118	today	MIT	A	93	Claude Code