review-plan

review-plan is a skill for Claude Code from 85danf/agent-skills. It costs 44 tokens per session (2,807 once invoked), scanned A, original, MIT.

A workflow for checking whether plan documents correctly match their source design, brainstorm, or requirements documents.

In plain words
What is it for?
Use it to classify design and plan files, map them into pairs, and coordinate reviews before executing the plans.
Why use it?
It removes the manual guesswork of deciding which files belong together and whether a plan is complete and accurate.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

Good fit Use it to classify design and plan files, map them into pairs, and coordinate reviews before executing the plans.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/85danf/agent-skills/review-plan
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 85danf/agent-skills --skill review-plan
Clone the repo
git clone --depth 1 https://github.com/85danf/agent-skills

Made for: Claude Code.

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-plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/85danf/agent-skills/review-plan/github.svg)](https://agentmods.dev/skills/85danf/agent-skills/review-plan)
Your own site
<a href="https://agentmods.dev/skills/85danf/agent-skills/review-plan"><img src="https://agentmods.dev/badge/skills/85danf/agent-skills/review-plan/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-plan

Your own site · 80×15
<a href="https://agentmods.dev/skills/85danf/agent-skills/review-plan"><img src="https://agentmods.dev/badge/skills/85danf/agent-skills/review-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,807 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 $0.00044 $0.02807
Opus 5.5 $0.00018 $0.01123
Sonnet 5.5 $0.00009 $0.00561
Haiku 4.5 $0.00004 $0.00281

Measured 1mo ago against content hash d65ab3269081, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-plan 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 1mo 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.

review-plan/SKILL.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Plan Against Design

Orchestrate a multi-lane review that a plan document is correctly derived from its source design, is internally feasible, and is grounded in the actual codebase — before the plan is executed.

This skill is the orchestrator only: it classifies inputs, gathers context, picks a run mode, dispatches reviewer lanes, and aggregates their findings. All review judgment lives in the references/lanes/*.md files. Never inline a lane's checklist here — read and run the lane.

Step 1: Classify input files

Split the provided files into designs and plans.

  • Plans: filename contains "plan".
  • Designs: filename contains "design", "architecture", "brainstorm", "spec", or "requirements".

If a file matches neither or both, ask the user which it is. If no design was provided, ask for one — the review compares plan against design and is far weaker without it. If the user confirms there is no design, proceed in no-design mode: record "no design provided" in the Context Summary, on panel skip Lane A entirely (five of its six checks need a design), and in every remaining dispatch prompt replace the design line with Design document(s): none — omit all design-fidelity checks. Solo keeps both its lanes — neither is design-only.

Step 2: Map designs to plans

  • 1 design + 1 plan → one pair, proceed.

  • 1 design + N plans → map all plans to that design.

  • N designs + M plans → ask the user for the mapping:

    Multiple design and plan docs found. Which design governs which plan(s)? Designs: {list} Plans: {list} Example: "design-auth -> plan-auth; design-api -> plan-api + plan-integration"

Step 3: Context round (always)

Before running anything, build shared context and measure complexity.

  1. Read every design and plan doc completely.
  2. Read project config: CLAUDE.md / AGENTS.md (and any it points to) for conventions, constraints, and preferred engineering standards. Project CLAUDE.md engineering preferences override the lanes' default rubric.
  3. Follow links: if a plan cites a PRD/RFC/ADR, read it.
  4. Skip file globbing here — the reviewer does its own grounding (the holistic lane on solo, the grounding lane on panel). Only note a path's status in the summary if the plan states it outright (marks a file "new"/"existing"), which needs no tool call.

Read the full file on GitHub · 242 lines

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. 1mo ago Changed · +115 lines · +18 tokens per session d65ab3269081
  2. 2mo ago First seen · 127 lines · 26 tokens per session scan A 9c56a8492619

Subscribe to this mod's changes

review-plan is a skill published in the GitHub repository 85danf/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 2,807 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 2026-08-31.

Related

review-plan compared with skills from other repositories

review-plan next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
review-plan85danf/agent-skillsSkill21mo agoMITA44Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex