critique

A design-document checker that compares DESIGN.md with the project's actual code and records findings in a separate report.

In plain words
What is it for?
Use it to check design structure, token usage, color contrast, accessibility, component states, dark mode, responsive layouts, and consistency.
Why use it?
It reveals when documented design rules are missing, unused, inconsistent, inaccessible, or different from the code.

Command for Codex

Part of the mddesign plugin — 5 skills, 10 commands, 5 agents, 4 hooks shipped together

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 commands/othmanadi/mddesign/critique
Clone the repo
git clone --depth 1 https://github.com/OthmanAdi/MDDesign

Made for: Codex.

Or install mddesign, the plugin that ships this one along with the rest of its 5 skills, 10 commands, 5 agents, 4 hooks.

Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 475 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.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.00475
Opus 5 $0.00024 $0.00237
Sonnet 5 $0.00010 $0.00095
Haiku 4.5 $0.00005 $0.00047

Measured 3d ago against content hash 56ba39ab3ba5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

critique 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 3d 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.

.codex/commands/critique.md · 44 lines

What it actually says

/mddesign:critique

Five-pass audit of the project's DESIGN.md against the actual code.

Passes

  1. Structural — delegate to npx @google/design.md lint --json. 7 Google linter rules.
  2. Drift — tokens declared but never used (orphans), colors/fonts used in code but not declared (leaks), near-duplicate tokens (ΔE < 5 for colors, ±1px for radii).
  3. Accessibility — WCAG AA/AAA contrast on declared color pairs, missing focus-ring token, missing reduced-motion fallback when animation tokens exist.
  4. Completeness — component states (hover/active/focus/disabled/error), dark-mode counterparts, responsive breakpoints.
  5. Consistency — spacing/radius/font-size scales check for geometric progression.

Output

Writes DESIGN.md.critique.md at project root, adjacent to DESIGN.md. Each finding has:

  • Stable id (F1, F2, ...)
  • Severity (P0 P1 P2 P3)
  • Category (structural / drift / accessibility / completeness / consistency)
  • Short title
  • Evidence (file paths, line numbers, counts)
  • Proposed fix
  • /mddesign:fix <id> slash command

Appends a one-line summary to progress.md.

Pre-flight

  • Glob DESIGN.md at project root. If absent, refuse with "Run /mddesign:harvest first."
  • Verify npx reachable.

Boundaries

  • Read-only on DESIGN.md (no edits).
  • Writes only DESIGN.md.critique.md (and appends to progress.md).
  • Never calls /mddesign:fix itself; that is a separate user action.

See skills/design-harvest/SKILL.md for the full five-pass logic.

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. 3d ago First seen · 44 lines · 49 tokens per session scan A 56ba39ab3ba5

Subscribe to this mod's changes

critique is a command published in the GitHub repository OthmanAdi/MDDesign (13 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 475 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.