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 agentmods add skills/getcrew44/crew44/design-handoffnpx skills add getcrew44/crew44 --skill design-handoffgit clone --depth 1 https://github.com/getcrew44/crew44Wrote 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/getcrew44/crew44/design-handoff)<a href="https://agentmods.dev/skills/getcrew44/crew44/design-handoff"><img src="https://agentmods.dev/badge/skills/getcrew44/crew44/design-handoff.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 | $0.00036 | $0.00598 |
| Opus 5 | $0.00018 | $0.00299 |
| Sonnet 5 | $0.00007 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
design-handoff 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 6d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Handoff
Produce a spec that lets the Coding Agent build the design without guessing. If it isn't specified, they'll have to invent — and they'll invent inconsistently.
Principles
- Tokens, not values. Reference
--space-4orcolor-primary-600, not16pxor#2563eb. If a value isn't in the system, flag that as a token gap, not a one-off. - Show every state. Default, hover, active, focus, disabled, loading, error, empty, success. A state you skip becomes a bug.
- Explain the why. "This collapses to a sheet on mobile because the action is one-handed" helps the engineer make sensible judgment calls when reality diverges from the spec.
- Specify edges, not just the happy path. Long text, no text, slow connection, partial data — pin the behavior.
Sections the spec must cover
- Overview. What this screen or component does, who uses it, and the user state when they encounter it.
- Layout. Grid, breakpoints, responsive behavior at each breakpoint. Where things move, hide, or change order.
- Tokens used. Color, typography, spacing, radius, shadow — listed with their token names and where they apply.
- Components. Each component named, with variants, props that matter for behavior, and any composition rules.
- States and interactions. Per element, the full state list with the visual change and trigger.
- Responsive behavior. What changes at each breakpoint. Not just "stacks on mobile" — what gets prioritized, what gets cut.
- Edge cases. Long copy, empty data, zero results, max items, slow connection, error states. The expected behavior for each.
- Motion. Per animated element: trigger, what moves, duration, easing. Honor
prefers-reduced-motion. - Accessibility. Focus order, ARIA labels and roles, keyboard interactions, screen reader announcements, contrast confirmations.
Common spec gaps that cause rework
- Loading and error states for async content.
- What happens when content overflows (truncate? wrap? scroll?).
- Empty state for collections that start empty.
- Behavior under slow or failed network.
- Keyboard shortcuts and tab order through complex layouts.
- Animation choreography across linked elements.
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.
- 6d ago First seen · 41 lines · 36 tokens per session scan A 4f8663ec147f
design-handoff is a skill published in the GitHub repository getcrew44/crew44 (359 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 598 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.
Other skills, from other repositories
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
zcode-delegate
Delegate a coding task to the Z.AI ZCode CLI as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to ZCode — phrasings like "have ZCode do X", "delegate this to ZCode", "run it through ZCode", or "use ZCode to implement/fix/refactor" — or…
mcp-scripting
Write mcpScript JavaScript for discovering, inspecting, and calling MCP tools.