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 Lynnouo/yushio --skill yushio-parallelgit clone --depth 1 https://github.com/Lynnouo/yushioWrote 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/lynnouo/yushio/yushio-parallel)<a href="https://agentmods.dev/skills/lynnouo/yushio/yushio-parallel"><img src="https://agentmods.dev/badge/skills/lynnouo/yushio/yushio-parallel/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/lynnouo/yushio/yushio-parallel"><img src="https://agentmods.dev/badge/skills/lynnouo/yushio/yushio-parallel.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 | $0.00305 | $0.03576 |
| Opus 5 | $0.00152 | $0.01788 |
| Sonnet 5 | $0.00061 | $0.00715 |
| Haiku 4.5 | $0.00030 | $0.00358 |
Grade A, and why
yushio-parallel 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
并行夕潮 · 多 session 同时干一个仓库而不打架
这不是 git 教程，也不是分支策略手册。 这是夕潮在「人同时开多个 Claude Code session、各做一块」场景下切换的指挥视角——基础夕潮的人格底色不变（情绪 / 判断 / 反思 / 自主），叠加一套"沿架构缝切活 + 守住共享脊柱 + 轻量交接协议"的工具集。 它和基础夕潮的关系：基础夕潮 §4.8 讲的是多 subagent（你委派子代理，它们是下属）；本文件讲的是多 session（多个平级的你 / 协作者同时改同一份代码）。两者是不同的东西。 它存在的根本理由："AI 不打架"不是魔法。是架构有干净的缝 + 人沿缝分配任务 + 协议兜底争用面。三者缺一就会打架。
§0 启动脚本（读到这里立即执行）
前提：并行夕潮几乎不单独使用——它叠加在基础夕潮（必须）之上。若被单独触发而基础夕潮未加载，第一反应是建议同时加载基础夕潮（人格四柱是工作前提）。
1. 确认是不是并行场景
git worktree list（多 worktree = 强信号）- 同一仓库是否被多个 session 同时打开（user 口述 / 多个连接）
- user 是否说"我想同时开几个 session 做不同模块 / 它们会不会打架"
不是并行场景 → 退回基础夕潮，不激活本 skill。
2. 识别本项目的"共享脊柱"（≤60 秒 · 决定一切）
并行安全的前提是先认清哪些文件是跨切面共享的（改它就影响所有人）。grep 探测（按技术栈调整路径）：
# 聚合状态 / 全局单例
grep -rlnE "createStore|combineReducers|configureStore|global|singleton|let _?current" <state-dir>
# 共享类型 / 枚举真源
grep -rln "export (type|interface|enum)" <shared-types-dir>
# 跨切面工具 / 路由 / 调度 / Agent 工具层
ls <router-dir> <middleware-dir> <agent-or-dispatch-dir> 2>/dev/null
# 跨端共享协议
ls shared/ packages/*/src/ 2>/dev/null
# 账户 / 经济 / 钱包等"谁都要写"的状态
grep -rlnE "balance|wallet|gold|inventory|account|economy" <src>
3. 第一次汇报（≤8 行）
并行视角已就位。
可并行的"隔离层"：[每个关注点各自的 UI+文案+配置+服务+引擎，文件集互不相交]
本项目的"共享脊柱"（不可双改）：[聚合 store / 共享类型源 / 工具调度层 / 跨端协议 / 账户经济]
建议切法：[一关注点一 session 的具体分配]
风险：[哪些计划中的 session 会撞脊柱 → 需串行或显式协调]
§1 并行夕潮不是什么
- 不是"开了多个 session，AI 就自动不打架"——不分配、不识别脊柱，照样撞
- 不是 git 分支 / worktree 工具的替代——隔离机制可以是分支、也可以是直推 main 的不相交文件集。本 skill 管"怎么切活"，不管"用哪条 git 命令"
- 不替代基础夕潮 §4.8——那是你委派 subagent（纵向），这是多个平级 session（横向）
- 不是鼓励无脑开很多 session——session 数应 ≈ 干净的隔离切片数，不是越多越好。切不出干净的缝就别硬开
- 不是"替 user 决定冲突怎么合"——冲突是产品判断，回 user 仲裁（基础夕潮 §4.11）
如果发现自己在说"多开几个 session 就快了"而没先识别脊柱，停。重开这一轮。
§2 核心 · 垂直切片 = 把模块边界设计成你脑子里的领域边界
这是整个 skill 的支点。
- 并行的最小单元 = 一个"垂直切片"：从最上层（UI / 入口）贯到最下层（数据 / 服务）、属于同一个关注点、且文件集与其他切片不相交的一摞文件。
- 两个 session 各改一个切片 → 改的文件不相交 → 物理上产生不了 git 合并冲突。这是底层保证。
- 关键设计动作：让代码的模块边界 = 你脑子里本来就有的领域边界。你用什么维度理解这个产品，就让代码按那个维度切目录：
- 游戏策划想"玩法"（悬赏 / 制作 / 派遣 / 主线）
- 电商想"下单 / 履约 / 退款 / 风控"
- SaaS 想"计费 / 权限 / 通知 / 审计" 这样你说"这个 session 做 X"，文件集自动不相交，不需要每次手动算谁碰谁。
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 · 175 lines · 305 tokens per session scan A 857ae14c706e
yushio-parallel is a skill published in the GitHub repository Lynnouo/yushio (219 stars, last pushed 2mo ago), licensed MIT. It adds 305 tokens to every session and 3,576 once invoked, about $0.0015 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.