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 Jaxton07/jax-skills --skill design-handoffgit clone --depth 1 https://github.com/Jaxton07/jax-skillsWrote 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/jaxton07/jax-skills/design-handoff)<a href="https://agentmods.dev/skills/jaxton07/jax-skills/design-handoff"><img src="https://agentmods.dev/badge/skills/jaxton07/jax-skills/design-handoff/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/skills/jaxton07/jax-skills/design-handoff"><img src="https://agentmods.dev/badge/skills/jaxton07/jax-skills/design-handoff.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 | $0.00115 | $0.01438 |
| Opus 5 | $0.00057 | $0.00719 |
| Sonnet 5 | $0.00023 | $0.00288 |
| Haiku 4.5 | $0.00012 | $0.00144 |
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 11d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
设计 + 交接流程(发起会话用)
把「想清楚 → 写下来 → 交给下一个会话」固化为三份产物:spec(决策层)、plan(文件级执行)、HANDOFF(新会话入口)。目录不存在就先建(mkdir -p)。
第 0 步:调研与验证(最重要,别跳过)
- 读项目索引与相关代码(若项目维护了
.local/docs/INDEX.md或根目录AGENTS.md/CLAUDE.md,先读它们)。 - 验证而非猜测:凡涉及 SDK/API/外部依赖行为的关键论断(函数签名、覆盖语义、默认值、扫描范围),必须读
node_modules/ 依赖包里的源码或.d.ts,或官方文档落实,并记录出处(文件:行)。 - 已有的 UI/基础设施要先盘点——很多时候「半边已经完工」(比如渲染层已有对应组件/解析逻辑),设计只需补缺的那半。
- 方案对比要有结论:列对比表,说明为什么否掉备选(如「子进程方案在打包态不可用」),不要只列可能性。
第 1 步:写 spec — .local/docs/design/spec/<主题>.md
决策层文档,回答「为什么这么做」,不含文件级任务拆分。结构惯例:
- 背景与现状盘点(已有什么、缺什么、为什么现成方案不可用)
- 目标 / 非目标(非目标写清本期边界,防实施会话膨胀范围)
- 核心决策(对比表 + 一句话机制)
- 架构与代码位置(目录结构、改动点归属哪个模块/包)
- 契约(参数 schema、跨模块/跨进程类型、数据形状——精确到字段)
- 安全清单(输入校验、权限、数据隔离等,按项目情况)
- 里程碑(P1/P2 分期)
- 风险与已验证事实:第 0 步验证的结论逐条列出处;验证不了的标为「待验证」,交给 plan 阶段 0
第 2 步:写 plan — .local/docs/design/plan/<主题>-plan.md
执行层文档,给实施会话照着做。结构惯例:
- 阶段 0 冒烟验证:把 spec 里每个「待验证」变成一个可执行断言脚本(最小可运行脚本 + 明确通过标准);卡点处理规则写死:失败回 channel 留言,不许绕过(后续决策依赖这些事实)
- 后续阶段按文件拆任务:每个任务写清新建/修改哪个文件、做什么、配什么测试
- 验收清单:项目自带的 lint / typecheck / test 全绿 + 逐项手测步骤 + 收尾纪律(关闭测试过程中起的服务/进程、更新项目索引)
- 「明确不做」清单(与 spec 非目标呼应)
- 引用 spec 而非重复其内容
第 3 步:建沟通频道 — .local/agent-work/channel/<主题>/HANDOFF.md
新会话的唯一入口,自包含、不依赖本次聊天记录。必含:
- 任务一句话 + 完成定义(= plan 验收清单全过 + 用户 review 通过)
- 必读文档顺序:HANDOFF → spec → plan →
AGENTS.md+ 项目索引(如有) - 关键约束:项目通用纪律(以仓库根
AGENTS.md/CLAUDE.md约定为准,如数据隔离、零破坏性变更、代码风格等)+ 本任务特有的硬约束(如递归防护、目录隔离) - 已验证事实表(事实 | 出处)——实施会话直接采信,禁止重复考证
- 待决策点:实施中遇到二选一时自行决策并记录进 IMPL-NOTES
- 沟通协议(见下)
沟通协议(写进 HANDOFF,跨会话只认文件不认聊天)
- 实施会话:进度/卡点/决策追加写
IMPL-NOTES.md(倒序、每条带日期时间、标注阶段);完成后写DONE.md(验收清单逐项打勾 + 改动文件清单 + 自测记录) - review 方:意见追加写
REVIEW.md;实施会话开工前先读它(存在的话) - spec/plan 与代码现状冲突 → 停下来在 channel 留言,不要自由发挥
第 4 步:收尾
不要把 spec/plan 文件写进项目索引(如 .local/docs/INDEX.md)——用户会不定期清理过时的 spec/plan,不一定记得同步索引,所以索引只标目录(design/spec/、design/plan/、channel/),不标单个文件。HANDOFF.md 里有完整路径,可发现性靠频道目录本身。
回复用户:交付物清单 + 关键决策摘要 + 「新会话从 channel 的 HANDOFF.md 进」。
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.
- 11d ago First seen · 69 lines · 115 tokens per session scan A 476519451b7b
design-handoff is a skill published in the GitHub repository Jaxton07/jax-skills (1 stars, last pushed 20d ago), licensed MIT. It adds 115 tokens to every session and 1,438 once invoked, about $0.0006 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 skills, from other repositories
visualkan
Generate visual explanations (whiteboard, infographic, presentation, diagram, mindmap, mockup) from any content, via native subscription image generation or an API backend (OpenAI, Gemini, OpenRouter, Grok).
visualkan-wizard
Walks the user through the Visualkan Controls one at a time, then starts the run. Use ONLY when the user names this skill directly, for example "/visualkan-wizard" or "run the visualkan wizard". Do NOT use this for a request to visualize, explain, diagram, sketch, or draw something. The visualkan skill owns those…
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
understand-figma
Analyze a Figma file via the Figma REST API and generate an interactive design knowledge graph (pages, screens, components, component sets, instances, design tokens) with a kind:"design" dashboard.
sxo
Search Experience Optimization (SXO) — the bridge between SEO and UX/CRO. Audits the full journey from the SERP click to the on-page goal: SERP click-through factors (title/meta/rich results that win the click), then post-click experience signals that keep users and drive conversions — above-the-fold relevance and…