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/bailutingyu/openbyline/handoff-protocolnpx skills add bailutingyu/OpenByline --skill handoff-protocolgit clone --depth 1 https://github.com/bailutingyu/OpenBylineWrote 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/bailutingyu/openbyline/handoff-protocol)<a href="https://agentmods.dev/skills/bailutingyu/openbyline/handoff-protocol"><img src="https://agentmods.dev/badge/skills/bailutingyu/openbyline/handoff-protocol.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 | $0.00096 | $0.05504 |
| Opus 5 | $0.00048 | $0.02752 |
| Sonnet 5 | $0.00019 | $0.01101 |
| Haiku 4.5 | $0.00010 | $0.00550 |
Grade A, and why
handoff-protocol 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 4d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
交接协议(handoff-protocol)
本系统的物理事实:在 Claude Code 里,每个 subagent 都有独立、全新的上下文窗口。父子之间唯一的通道只有两根线——
- 父调用子时传入的 prompt 字符串;
- 子返回给父的 最终消息。
除此之外,agent 之间什么都看不到:你脑子里的上下文、你刚读过的文件、上一轮的讨论,子 agent 一概不知。
结论也只有一句:一切要跨 agent 共享的东西,都必须落盘成 workspace/ 下的 Markdown artifact。 口头说、靠上下文带、写在 prompt 里"我之前提到过"——全部会丢。
一、核心原则(4 条铁律)
- 以 artifact 为准(Single Source of Truth):任何 agent 的输入和输出,都以
workspace/下的 Markdown 文件为准。没落盘 = 不存在。 - prompt 只传指针,不传内容:主编调用专家时,prompt 里写"去读哪个文件、去写哪个文件、本轮目标和约束",而不是把上游内容整段复制进去。专家自己用 Read 工具去读 artifact。
- 专家只写自己负责的 artifact:一个 artifact 只有一个 author-agent。要改别人的产物,不许直接覆盖——写进
review-log.md,由原作者返工。 - 不编造:任何事实/数据/引用都要带来源标注;查不到就标
[待核]或[未证实],绝不硬编。详见第四节。
二、主编调用专家的 prompt 强约束
主编(zhubian-orchestrator)每次调用专家,prompt 必须显式写明 4 件事,缺一不可:
- 要读哪些 artifact:给出绝对路径列表(上游依赖)。
- 要产出哪个 artifact:给出本轮要写/更新的目标文件绝对路径。
- 本轮目标:一句话说清这次要交付什么。
- 约束与边界:标准(如写作品控标准)、字数、禁止项、本轮不做什么。
路径约定:prompt 里一律给绝对路径(让专家少猜);artifact YAML 头的
upstream字段里则只写workspace/下的文件名(便于整库迁移)。两者指向同一个文件,不冲突。
标准调用 prompt 模板(照抄)
模板里的【专家角色名】用
.claude/agents/下的真实 agent name(如 outline-architect / drafter / researcher),不要用"结构专家"这类口语别名——这样专家落盘时 author-agent 才能回查到真实 agent。
你是【专家角色名,用真实 agent name,如:outline-architect / drafter】。
【要读的上游 artifact(先用 Read 读完再动手)】
- /…/workspace/voice-profile.md
- /…/workspace/topic-brief.md
- /…/workspace/research-dossier.md
【本轮目标】
基于以上材料,产出/更新 outline.md:一个开宗明义、单层逻辑、一文一中心的提纲。
【要产出的 artifact】
- 写到:/…/workspace/outline.md
- 文件顶部必须带本协议第三节规定的 YAML 头(status 先填 draft)。
【约束】
- 严格遵守写作品控标准:对象感(用"你")、赋能、单层逻辑、开头亮中心。
- 不要扩写成正文;只做提纲。
- 任何事实/数据带 [来源: …];查不到标 [待核],不许编。
【返回给我(最终消息)】
- 你写入的 artifact 绝对路径;
- 3 句话内的自评:达成了什么、哪里还弱、下一步建议交给谁。
专家的返回消息也要克制:只回"写到了哪个路径 + 极简自评 + 风险/缺口"。不要把正文整段贴回来——正文在文件里,主编自己会去读。
三、artifact 顶部 YAML 头规范
每个会流向下游的核心 artifact(voice-profile / topic-brief / research-dossier / story-bank / outline / draft-v{n} / final)第一行起必须是 YAML 头;工作笔记型产物(review-log / headlines / punchlines / final-qc-report)用 §六 等各自规定的格式即可,不强制 YAML 头。核心 artifact 的 YAML 头中,
stage / author-agent / version / status / upstream 为必填(与 CLAUDE.md §三 一致),
updated 可选(建议填,便于追溯);个别 skill 可加自有可选字段(如 structure-templates 的 template)。
字段如下(author-agent 一律用 .claude/agents/ 下真实存在的 agent name):
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.
- 4d ago First seen · 273 lines · 96 tokens per session scan A 3eedc8b16a89
handoff-protocol is a skill published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 2mo ago), licensed MIT. It adds 96 tokens to every session and 5,504 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…