lunar-claude: Command for Claude Code

.claude/commands/design-validation/self-critique-design-review.md

self-critique-design-review is a command for Claude Code from basher83/lunar-claude. It costs 7 tokens per session (1,281 once invoked), scanned A, original, MIT.

A command for reviewing a design in two phases: an initial assessment followed by deliberate self-criticism. It saves the review as a document in a specified folder.

In plain words
What is it for?
Assessing a design document, recording three strengths and three concerns, challenging the first assessment, and producing a recommendation.
Why use it?
It forces the reviewer to examine both strengths and concerns, helping expose blind spots before implementation.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

This is basher83/lunar-claude's own configuration. It tells Claude Code how to work on lunar-claude 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 lunar-claude configures →

Reuse

Borrowing it

Nothing to install: this file belongs to basher83/lunar-claude. 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/basher83/lunar-claude/main/.claude/commands/design-validation/self-critique-design-review.md
Clone the repo
git clone --depth 1 https://github.com/basher83/lunar-claude

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 self-critique-design-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/basher83/lunar-claude/self-critique-design-review/github.svg)](https://agentmods.dev/commands/basher83/lunar-claude/self-critique-design-review)
Your own site
<a href="https://agentmods.dev/commands/basher83/lunar-claude/self-critique-design-review"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/self-critique-design-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 self-critique-design-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/basher83/lunar-claude/self-critique-design-review"><img src="https://agentmods.dev/badge/commands/basher83/lunar-claude/self-critique-design-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,281 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 $0.00007 $0.01281
Opus 5 $0.00003 $0.00641
Sonnet 5 $0.00001 $0.00256
Haiku 4.5 $0.00001 $0.00128

Measured 12d ago against content hash d73ac7b55022, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

self-critique-design-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.

.claude/commands/design-validation/self-critique-design-review.md · 220 lines

How it starts

The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Conduct a rigorous two-phase design review with explicit self-critique to reduce confirmation bias. This process forces you to challenge your own assessment, identify blind spots, and produce a validated recommendation with clear confidence levels.

Use this command BEFORE committing to implementation to catch design flaws early.

Variables

DESIGN_DOCUMENT: $1 OUTPUT_DIR: docs/reviews/design-validation/self-critique-design-review/ FILE_NAME: <two-to-three-words-from-DESIGN_DOCUMENT-filename>.md

Instructions

  • IMPORTANT: If no DESIGN_DOCUMENT is provided, stop and ask the user to provide it.
  • Verify OUTPUT_DIR exists, create it if it doesn't.
  • Save output from review to OUTPUT_DIR/FILE_NAME.
  • Conduct a two-phase review with explicit self-critique to reduce confirmation bias.

Workflow

Phase 1: Initial Assessment

Analyze the design document and produce:

1.1 Design Strengths (identify exactly 3)

For each strength, document:

  • What aspect of the design is strong
  • Why it effectively addresses requirements
  • Specific evidence or examples supporting this

1.2 Design Concerns (identify exactly 3)

For each concern, document:

  • What assumption or decision needs scrutiny
  • Why this could be a risk or limitation
  • What research or validation would address it

1.3 Integration vs. Build Analysis

Answer these questions explicitly:

  • Have we identified existing solutions that solve this or parts of it?
  • What specific evidence shows existing solutions won't work?
  • What are we planning to build that might already exist?

Phase 2: Self-Critique

Challenge your Phase 1 assessment by working through each category:

2.1 Bias Check

  • Am I defending this design because I created it vs. objectively evaluating it?
  • What assumptions am I making without evidence?
  • Have I researched alternatives thoroughly enough?
  • Am I overestimating our ability to build vs. integrate?

2.2 Blind Spots

  • What did I miss in the landscape research?
  • What edge cases or failure scenarios haven't been considered?
  • What stakeholder perspectives aren't represented?
  • What technical constraints haven't been validated?

Read the full file on GitHub · 220 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. 12d ago First seen · 220 lines · 7 tokens per session scan A d73ac7b55022

Subscribe to this mod's changes

self-critique-design-review is a command published in the GitHub repository basher83/lunar-claude (23 stars, last pushed today), licensed MIT. It adds 7 tokens to every session and 1,281 once invoked, about $0.0000 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.