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.
git clone --depth 1 https://github.com/Muminur/frontend-design-craft-skillWrote 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.
[](https://agentmods.dev/commands/muminur/frontend-design-craft-skill/critique)<a href="https://agentmods.dev/commands/muminur/frontend-design-craft-skill/critique"><img src="https://agentmods.dev/badge/commands/muminur/frontend-design-craft-skill/critique.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00010 | $0.00456 |
| Opus 5 | $0.00005 | $0.00228 |
| Sonnet 5 | $0.00002 | $0.00091 |
| Haiku 4.5 | $0.00001 | $0.00046 |
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 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.
What it actually says
/critique
Pure UX review. Identify what does not earn its place, what is unclear, what fights for attention. Report only — pair with /distill or /polish to act on findings.
Target
$ARGUMENTS
Procedure
- The squint test. Look at the screen with eyes squinted. What dominates? Is it the most important thing? If not, hierarchy is broken.
- The five-second test. What does the page communicate in five seconds? Does it match the product's actual proposition?
- Cognitive load. Count the number of decisions the user has to make per screen. More than 3 is usually too many on a marketing page; more than 5–7 on a product UI.
- Information architecture. Is content grouped logically? Are related items near each other? Are unrelated items separated?
- What can be removed? For each element on the screen, ask: if this disappeared, would the user notice? Would the product be worse? If both answers are no, propose removal.
- Calls to action. Is there one primary CTA per viewport? If there are two primaries, one of them is not primary.
- Empty states and edge cases. What happens with no data? With long content? With error states? Are these designed or generated?
- Accessibility from a UX angle. Are interactive elements obvious? Do focus states exist? Can the page be operated with a keyboard?
Output
## Critique: [target]
### Hierarchy
- [observation, severity]
### Clarity
- [observation, severity]
### Cognitive load
- [score: low/medium/high] — [reasoning]
### Candidates for removal
- [element, reason]
### Missing states
- [empty / loading / error coverage]
### One thing to change first
- [single highest-leverage fix]
End with the single highest-leverage change. Do not list ten things if only one matters.
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.
- 7d ago First seen · 50 lines · 10 tokens per session scan A 856e73be3640
critique is a command published in the GitHub repository Muminur/frontend-design-craft-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 456 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
profile
Save, load, inspect, update, reset, or delete diagram-design client profiles.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
team-ui
Orchestrate UI/UX design team.
p3-ux-wireframes
Creates wireframes (ASCII art) for the most important screens with interaction descriptions.