metaswarm: Command for Claude Code

.claude/commands/review-design.md

review-design is a command for Claude Code from dsifry/metaswarm. It costs 0 tokens per session (1,009 once invoked), scanned A, original, MIT.

A command that reviews a design document through separate product, architecture, design, security, and technical-lead checks.

In plain words
What is it for?
It checks the document, runs five reviews in parallel, combines their results, and reports blockers, suggestions, and next steps.
Why use it?
It brings together feedback on user needs, technical structure, usability, security, and readiness before implementation begins.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is dsifry/metaswarm's own configuration. It tells Claude Code how to work on metaswarm itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything metaswarm configures →

Part of the metaswarm plugin — 14 skills, 16 commands, 2 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to dsifry/metaswarm. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dsifry/metaswarm/main/.claude/commands/review-design.md
Clone the repo
git clone --depth 1 https://github.com/dsifry/metaswarm

Made for: Claude Code.

Or install metaswarm, the plugin that ships this one along with the rest of its 14 skills, 16 commands, 2 hooks.

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-design

README.md
[![agentmods](https://agentmods.dev/badge/commands/dsifry/metaswarm/review-design.svg)](https://agentmods.dev/commands/dsifry/metaswarm/review-design)
Your own site
<a href="https://agentmods.dev/commands/dsifry/metaswarm/review-design"><img src="https://agentmods.dev/badge/commands/dsifry/metaswarm/review-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,009 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 $0.00000 $0.01009
Opus 5 $0.00000 $0.00504
Sonnet 5 $0.00000 $0.00202
Haiku 4.5 $0.00000 $0.00101

Measured 7d ago against content hash 962d567c1c2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-design 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 7d 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.

.claude/commands/review-design.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Design Command

Run the design review gate on a design document to get feedback from Product Manager, Architect, Designer, Security Design, and CTO agents.

Usage

/review-design <path-to-design-doc>

Examples

# Review a specific design document
/review-design docs/plans/2026-01-11-contact-assistant-design.md

# Review the most recent design document
/review-design --latest

# Re-run review after revisions
/review-design docs/plans/2026-01-11-contact-assistant-design.md --iteration 2

What This Does

  1. Validates the design document exists and is in the expected format
  2. Spawns five review agents in parallel:
    • Product Manager Agent - Validates use cases and user benefits
    • Architect Agent - Reviews technical architecture
    • Designer Agent - Reviews UX, API design, developer experience
    • Security Design Agent - Reviews security threats and mitigations
    • CTO Agent - Reviews TDD readiness, codebase alignment
  3. Aggregates results from all five agents
  4. Reports outcome with blockers, suggestions, and next steps

Arguments

Argument Description
<path> Path to design document (required unless --latest)
--latest Review most recent design doc in docs/plans/
--iteration N Mark as iteration N of review cycle
--skip-agent <name> Skip specific agent (pm, architect, designer, security, cto)

Review Verdicts

APPROVED

All agents approve. Output includes:

  • Summary of what each agent reviewed
  • Non-blocking suggestions for future improvement
  • Next steps for implementation

NEEDS_REVISION

One or more agents found blocking issues. Output includes:

  • List of blocking issues by agent
  • Questions requiring clarification
  • Iteration count (max 3 before escalation)

Read the full file on GitHub · 181 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. 7d ago First seen · 181 lines · 0 tokens per session scan A 962d567c1c2b

Subscribe to this mod's changes

review-design is a command published in the GitHub repository dsifry/metaswarm (413 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,009 tokens. 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.