Kiro Crew is a persistent development workspace where agents continue multi-step software work across sessions, schedules, and connected interfaces. Developers use it locally or remotely through a desktop app, web dashboard, CLI, Slack, or Discord, with unattended tasks and recurring jobs. The catalogue contains skills and instructions for working with this workspace.
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.
npx skills add kirodotdev/KiroCrew --skill design-critiquegit clone --depth 1 https://github.com/kirodotdev/KiroCrewWrote 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/skills/kirodotdev/kirocrew/design-critique)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/design-critique"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/design-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 | $0.00131 | $0.06237 |
| Opus 5 | $0.00066 | $0.03119 |
| Sonnet 5 | $0.00026 | $0.01247 |
| Haiku 4.5 | $0.00013 | $0.00624 |
Grade A, and why
design-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.
How it starts
The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Critique — automated heuristic evaluation
Act as an experienced designer running a heuristic evaluation — a fellow designer looking over the work, not an authority handing down a verdict. This is an expert review, not user research and not an accessibility certification. Inspect the supplied design against established heuristics, rate evidenced issues, and recommend concrete design directions.
When to use
The user provides an image (screenshot / Figma export / mockup), Figma design, rendered HTML, URL, or multi-screen flow and asks for a design, usability, or heuristic review.
Prime directive
Evaluate the supplied artifact, not an imagined product. Do not penalize unprovided screens, states, breakpoints, or flows. You MAY flag an absent label, cue, affordance, or feedback mechanism when the supplied artifact gives enough context to show it is required. Every finding must cite observable evidence from the supplied artifact. Do not speculate.
Step -1 — Establish the evaluation brief
Severity and relevance depend on context. Before scoring, capture:
- Target users and relevant abilities or domain knowledge
- Primary task / intended outcome
- Product and screen type (consumer app, dashboard, checkout, settings, etc.)
- Platform, viewport, and input method when known
- Design maturity (concept, draft, release candidate)
- Known constraints (brand, design system, regulatory, localization)
Use context the user already supplied. If something is missing, infer only low-risk facts from the artifact and list them as assumptions. Ask a concise clarifying question only when different answers would materially change severity or the overall read. Never invent frequency data; describe frequency as expected exposure under the stated or assumed task.
Step 0 — Detect input type and evaluability
Classify the evidence before evaluating it:
| Input | Assessable | Not assessable without more evidence |
|---|---|---|
| Image / screenshot | Visual craft, layout, visible content, relative prominence, likely contrast or target-size concerns | Exact dimensions/ratios, DOM semantics, keyboard/focus behavior, interaction feedback, unshown flows |
| Figma design | Image checks plus declared dimensions, colors, and component structure when design context is available | Runtime semantics and behavior unless prototyped |
| Rendered code / markup / URL | Image checks plus computed styles, dimensions, DOM semantics, and runtime interaction checks | Unprovided multi-screen flows |
| Multiple screens / flow | Adds system status, control, recovery, continuity, and end-state evaluation | Unshown branches or behaviors |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- frameworks/main-checklist.md 16 KB
- scripts/.gitignore 32 B
- scripts/capture-build.mjs 16 KB runs code
- scripts/capture-site.mjs 6.9 KB runs code
- scripts/discover-routes.mjs 6.4 KB runs code
- scripts/ensure-playwright.mjs 3.4 KB runs code
- scripts/render.mjs 6.4 KB runs code
- scripts/ssrf-guard.mjs 7.0 KB runs code
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 · 470 lines · 131 tokens per session scan A d68ddc952415
design-critique is a skill published in the GitHub repository kirodotdev/KiroCrew (3,667 stars, last pushed today), licensed Apache-2.0. It adds 131 tokens to every session and 6,237 once invoked, about $0.0007 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.
Other skills, from other repositories
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
concept-diagrams
Minimal SVG diagrams as standalone HTML files.
frontend-design
Create distinctive, production-grade frontend interfaces.
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
review-animations
Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.