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 devcxl/mattpocock-skills-zh --skill claude-handoffgit clone --depth 1 https://github.com/devcxl/mattpocock-skills-zhWrote 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/devcxl/mattpocock-skills-zh/claude-handoff)<a href="https://agentmods.dev/skills/devcxl/mattpocock-skills-zh/claude-handoff"><img src="https://agentmods.dev/badge/skills/devcxl/mattpocock-skills-zh/claude-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/devcxl/mattpocock-skills-zh/claude-handoff"><img src="https://agentmods.dev/badge/skills/devcxl/mattpocock-skills-zh/claude-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00308 |
| Opus 5 | $0.00013 | $0.00154 |
| Sonnet 5 | $0.00005 | $0.00062 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
claude-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.
What it actually says
为当前对话撰写一份交接摘要，让一个全新的 agent 能够继续工作。不要把摘要保存到本地，而是启动一个后台 agent，把这份摘要作为它的提示词注入：claude --bg --name "<描述性名称>" "<交接摘要>"。它会在当前工作目录启动并立刻返回；用户通过 claude agents 来管理它。
务必传 -n/--name 并配以描述性名称（例如 --name "修复登录 bug"）：它会被设置为任务列表、会话选择器以及终端标题中所显示的标签。
在摘要里加一个 "suggested skills" 部分，建议下一个 agent 调用哪些技能。
不要重复已经被记录在其他产物（规格、计划、ADR、issue、commit、diff）中的内容。引用时用路径或 URL。
抹去任何敏感信息，例如 API 密钥、密码或可识别个人身份的信息：摘要会成为 agent 的提示词。
如果用户传入了参数，把它们当作对下一个会话关注点的描述，并据此裁剪摘要。
What ships with it
1 file 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.
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 · 19 lines · 25 tokens per session scan A bc2aa7b9fab5
claude-handoff is a skill published in the GitHub repository devcxl/mattpocock-skills-zh (340 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 308 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 2026-08-30.
Other skills, from other repositories
video-notes-generator
Summarize video URLs or local videos into timestamped Markdown notes from complete transcripts and actual visual evidence, with adaptive sampling and targeted visual follow-up. Supports Bilibili, YouTube, Douyin and Kuaishou.
zuiti-persona-template
A personalized version of a difficult-message reply helper that explains possible subtext, assesses misunderstanding risk, and drafts replies in the user's usual style.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
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.
social-media-strategy
Platform-specific tactics, content optimization, audience growth, and analytics-driven social media strategy. Use when planning a social strategy, optimizing posts for a specific platform, or growing and measuring an audience.
ui-ux-design-expert
Expert guidance on UI/UX design, design systems, accessibility (WCAG 2.2), user research, and creating inclusive, user-centered interfaces with 2025 best practices. Use when designing or auditing an interface, building a design system, or checking accessibility against WCAG 2.2.