A workflow that sends a software implementation plan to several reviewers at once and combines their findings into a saved report. The reviewers can represent different stakeholder perspectives, such as security, testing, or maintainability.

Use it to review a saved plan, check whether it is ready to implement, and create a structured findings file for later fixes.

It helps uncover missing work, risks, and disagreements before coding begins. It preserves differing opinions instead of silently choosing between them.

plan-review — Skill for Claude Code by wsauret: A workflow that sends a software implementation plan to…

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.

agentmods

npx agentmods add skills/wsauret/flywheel/plan-review

Any agent

npx skills add wsauret/flywheel --skill plan-review

Clone the repo

git clone --depth 1 https://github.com/wsauret/flywheel

Made for: Claude Code.

Or install flywheel, the plugin that ships this one along with the rest of its 15 skills, 15 agents.

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/wsauret/flywheel/plan-review.svg)](https://agentmods.dev/skills/wsauret/flywheel/plan-review)

Your own site

<a href="https://agentmods.dev/skills/wsauret/flywheel/plan-review"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/plan-review.svg" alt="Measured on agentmods" height="20"></a>

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,273 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00039	$0.03273
Opus 5	$0.00019	$0.01636
Sonnet 5	$0.00008	$0.00655
Haiku 4.5	$0.00004	$0.00327

Measured 6d ago against content hash 568388e66d77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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.

flywheel/skills/plan-review/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Reviewing Skill

Run ALL available reviewer agents in parallel, collect their prose findings, structure them into the schema, dedup semantically, and write a merged findings.json into the active session directory.

Philosophy: Each reviewer represents a different stakeholder perspective. These perspectives legitimately conflict. We do NOT resolve conflicts — we preserve them as distinct findings and surface disagreements for the user to decide.

Architecture: Reviewers return natural-language prose; the synthesizer (this skill) is the single schema enforcer. Reviewers focus on finding issues; structuring is the synthesizer's job.

Input

Plan identifier via $ARGUMENTS. If empty, the skill reads the active session pointer at .flywheel/plugin/active.json and loads that session's spec.json as the review target.

If .flywheel/plugin/active.json does not exist, error with:

No active session. Run /plan first.

Phase 0: Load Target & Project Context

If $ARGUMENTS is non-empty, treat as a plan path.
Otherwise: read .flywheel/plugin/active.json, extract session_id, load .flywheel/plugin/sessions/<session_id>/spec.json.
The review target (plan content or spec content) is passed inline to the reviewers.
Use Glob to find the project's architectural docs once at the orchestrator level — reviewers read the resulting paths instead of doing six parallel discoveries: CLAUDE.md, agents.md, docs/architecture.md, docs/adrs/**/*.md, docs/coding-guidelines*.md. Collect into PROJECT_CONTEXT_PATHS and inline them in every reviewer dispatch under "PROJECT CONTEXT PATHS." If no docs match, pass none.

Plan reviewers: reviewer-architecture, reviewer-code-quality, reviewer-patterns, reviewer-performance, reviewer-data-integrity, reviewer-elegance.

Reviewers may catch external claim issues (version mismatches, anti-patterns, security concerns) as part of their normal review. There is no separate enrichment step — plan-creation handles initial validation; reviewers provide a second check from their respective perspectives.

Read the full file on GitHub · 257 lines

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/conflict-handling.md 1.7 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.

6d ago First seen · 257 lines · 39 tokens per session scan A 568388e66d77

Subscribe to this mod's changes

plan-review is a skill published in the GitHub repository wsauret/flywheel (14 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 3,273 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 2026-08-30.

Planning ai claude-code-plugin coding-agent terminal-ui tui

contributor-onboarding

Help a new contributor get productive on this checkout - inspect sync state against main, build, run the repository's exact verification gate, and produce a local what's-new digest. Never fetches, pulls, or modifies a dirty tree on its own. Explicit-only.

Hmbown/CodeWhale · 57 tokens

handoff

Write a compact, decision-ready handoff so the next session (or the user) can continue without reconstructing the current one. Use when the session is ending, context is running low, the user asks for a handoff / "pass the baton" / "hand off", or a long-running operation needs a durable state checkpoint.

Hmbown/CodeWhale · 70 tokens

plan-review