Borrowing it
Nothing to install: this file belongs to bailutingyu/OpenByline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bailutingyu/OpenByline/main/.claude/skills/ultracode-orchestration/SKILL.mdgit 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/ultracode-orchestration)<a href="https://agentmods.dev/skills/bailutingyu/openbyline/ultracode-orchestration"><img src="https://agentmods.dev/badge/skills/bailutingyu/openbyline/ultracode-orchestration/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/bailutingyu/openbyline/ultracode-orchestration"><img src="https://agentmods.dev/badge/skills/bailutingyu/openbyline/ultracode-orchestration.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 | $0.00124 | $0.03484 |
| Opus 5 | $0.00062 | $0.01742 |
| Sonnet 5 | $0.00025 | $0.00697 |
| Haiku 4.5 | $0.00012 | $0.00348 |
Grade A, and why
ultracode-orchestration 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 9d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
并行编排原语手册（ultracode-orchestration）
本 skill 提供写作流水线的确定性多智能体并行编排原语——在该并行处并行、在该串行处串行、在该停下来问人处停下来，依赖决定串并行，不为并行而并行。
人是主编，AI 是执行者，AI 交付的永远是初稿；并行只让执行更快更稳更不漏，不改变"人定方向、人定稿"。
一、两条真实可落地的执行路径（先认清物理事实）
Claude Code 里能真正"并发跑多个专家"的机制只有两条。
路径 A · Workflow 工具（主编=主程序时的旗舰路径）
当用户直接对主程序（顶层 Claude Code）说"写一篇…"、且开了 ultracode 时，主程序本身就是主编，用 Workflow 工具把整条流水线写成一个 JS 编排脚本：
parallel([thunkA, thunkB, …])：真正并发跑多个专家（barrier，等齐再返回）。pipeline(items, stage1, stage2, …)：每个条目独立流过多阶段，无阶段间 barrier（默认）。agent(prompt, {agentType:'fact-checker', schema, label, phase})：把本项目的专家 agent（drafter / fact-checker / style-aligner …）作为 workflow agent 拉起；agentType直接复用.claude/agents/里的角色。schema让专家返回结构化结果（免解析）。- 专家在 workflow 里仍按 handoff-protocol 把 artifact 写进
workspace/内容输出/<slug>/，返回值只回一个指针+极简自评。 - 本项目可复用的整流水线脚本见 newArtifact
write-pipeline.workflow（长稿一键启全 DAG、三处人类 gate 自动暂停；短稿退化为三步串行）。
路径 B · 并行 Task 调用（主编=orchestrator subagent 时）
当主编是 zhubian-orchestrator subagent（它没有 Workflow 工具）时，用在同一条消息里发出多个 Task 调用来并发——这是 Claude Code 的原生行为：一条回复里若干个无依赖的 Task 会并行执行。
- fan-out：一条消息里对 researcher / story-curator / knowledge-manager 各发一个 Task → 三个专家并发。
- barrier：等这一批 Task 全部返回后，主编自己在下一步把它们的产物汇聚。
- 每个并行分支只写自己独立的 fragment 文件（见 §三），主编再单点合并——零竞态，不依赖任何实验旗标。
选哪条？用户直接找主程序写稿、ultracode 开 → 路径 A（Workflow）。已经进了 orchestrator subagent 上下文、或环境不便用 Workflow → 路径 B（并行 Task）。两条路径的编排拓扑、原语、并发安全规则完全一致，只是落地 API 不同。
二、八个编排原语
| 原语 | 一句话 | 用在写作流水线哪里 |
|---|---|---|
| fan-out | 把无依赖的活拆成 N 个分支并发跑 | 取材三源 / 三道审查 / 点睛(标题+金句) / 长稿分节 / 多平台排版 |
| barrier | 等一批分支全部完成再往下 | 取材后收口、审查后判 Critical、分节后汇稿 |
| join | 下游节点等齐所有上游产物才启动 | outline 等齐取材、final-qc 等齐审查+点睛 |
| fragment-then-merge | 每分支写独立文件，单一汇聚者合并 | 一切并行落盘的通用安全规则（§三） |
| judge-panel | 多候选并行生成 → 多评委按 rubric 投票择优 | 标题 / 金句 / 案例类比 / 选题角度 / 画像指纹 |
| loop-until-dry | 反复跑直到一轮无新增，再停 | 事实核查（抽取→核验→自问→红队，直到 0 新增 Critical） |
| completeness-critic | 终关核对上游覆盖率而非复述结论 | final-qc 核断言清单 100%、逻辑覆盖 outline 全点 |
| adversarial-redteam | 独立第二视角专门找反证/反例 | 每道审查的 redteam pass、关键数字多源交叉、judge 去偏 |
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.
- 9d ago First seen · 137 lines · 124 tokens per session scan A 34c19039e07c
ultracode-orchestration is a skill published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 2mo ago), licensed MIT. It adds 124 tokens to every session and 3,484 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…