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/obiwancenobi/klambenWrote 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/obiwancenobi/klamben/critique)<a href="https://agentmods.dev/commands/obiwancenobi/klamben/critique"><img src="https://agentmods.dev/badge/commands/obiwancenobi/klamben/critique/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.
<a href="https://agentmods.dev/commands/obiwancenobi/klamben/critique"><img src="https://agentmods.dev/badge/commands/obiwancenobi/klamben/critique.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00031 | $0.00541 |
| Opus 5 | $0.00015 | $0.00270 |
| Sonnet 5 | $0.00006 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
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 9d 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
Subjective UX critique of a screen or widget. Not a linter — a design review.
When to use
- User asks "how does this look" / "is this good UX" / "what would you change"
- Before a visual design review
- After
/auditis clean but the UX still feels off
Process
- Check design context: If
.klamben.mdexists in the project root, read it first. Apply the project's brand, platform targets, accessibility tier, and existing patterns to your work below. - Read the target widget file
- Build a mental model of the rendered layout (visual hierarchy, grouping, flow)
- Apply principles from
skill/references/(especially spacing, typography, interaction, ux-writing) - Review for:
- Hierarchy: Is the primary action obvious? Is less-important content visually recessed?
- Grouping: Are related elements close? Are unrelated elements separated?
- Affordance: Is it clear what's tappable? Are disabled states distinguishable?
- Copy: Are button labels verbs? Are errors actionable?
- Flow: Does the user's eye follow a sensible path?
- Do not modify any file. Write comments only.
Output format
Critique of home_screen.dart
HIERARCHY
- "Save" is the primary action but rendered as OutlinedButton.
Consider FilledButton to match its importance.
- Card headers all use titleMedium — consider titleLarge for the top
one to create a clear anchor.
GROUPING
- Name field and avatar are visually distant. Moving avatar above name
would match user mental model ("this is about [person]").
AFFORDANCE
- The gray row at L47 has an onTap but no ripple or chevron.
Users won't know it's tappable. Add InkWell + trailing chevron icon.
COPY
- Button "Submit" (L62) → "Send feedback"
- Error "Try again" (L89) → "Couldn't send. Check your connection and
try again."
FLOW
- The save CTA is below the fold on small phones. Sticky it to the
bottom or move it above the optional fields.
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.
- 9d ago First seen · 68 lines · 31 tokens per session scan A 73fe3cb807ae
critique is a command published in the GitHub repository obiwancenobi/klamben (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 541 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 2026-08-31.
Other commands, from other repositories
brainstorm
Design-first ideation workflow that explores user intent, clarifies constraints, proposes approaches, and produces an approved design document before planning.
design
Design workflow that creates design systems, DESIGN.md, and design tokens with anti-pattern enforcement and accessibility checks.
ar-ph
Refresh the universal system design philosophy before designing or reviewing code.
my_brand
Interactive brand identity creation with archetypes, colors, typography, and voice guidelines. Use when user mentions "brand", "colors", "typography", "brand.md", "design system", or "visual identity".
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.