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 0fuk/OpenACCP --skill coordination-worktreegit clone --depth 1 https://github.com/0fuk/OpenACCPWrote 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/0fuk/openaccp/coordination-worktree)<a href="https://agentmods.dev/skills/0fuk/openaccp/coordination-worktree"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/coordination-worktree/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/0fuk/openaccp/coordination-worktree"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/coordination-worktree.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 | $0.00141 | $0.01871 |
| Opus 5.5 | $0.00056 | $0.00748 |
| Sonnet 5.5 | $0.00028 | $0.00374 |
| Haiku 4.5 | $0.00014 | $0.00187 |
Grade A, and why
coordination-worktree 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 2d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/coordination-worktree — 文件信箱通讯层 + worktree 工作模式
存在理由:多会话协作里,平台的会话间消息要么需人工点确认、要么在空闲期送不到;一个共享目录+一套命名约定,是唯一实证在无人值守下也能可靠送达、可审计、可回放的通道。worktree 则让每条线在同一仓里互不踩脚。项目具体路径读项目根 PROJECT-PROFILE.md。
一、协调目录=通讯层
- 一个项目一个协调目录(如
<项目>/coordination/),扁平存放,历史件按月归档到_archive/YYYYMM/(Monitor 只扫顶层)。落盘即送达,收件=对方 Monitor 叫醒后消费;不发平台消息、不点确认框。 - 文件名即路由:
致<收件角色>-<发件角色>-<件型>-<主题>-<YYYYMMDD-HHMM>.md(定向件);<角色>-<件型>-<主题>-<HHMM>.md(该角色的产出件)。角色 token 必须出现在文件名里,各角色的 Monitor pattern 按角色 token 收件并从真实文件名回测(见 /moniter-on)。 - 固定的文件类型清单:执行令/一行令(派活)·回执(收到并将做什么)·进度(30 分钟一落或转折时)·交回(完工,六节:目标与出处/改动清单/红绿验证(先复现出错再验证修好)/测试证据/规范或文档摘要/自检与遗留)·探活(对端疑死)·注记(主动提醒,不要求回复)·SELFTEST(通道实测(发一个真事件看它能否回到会话),阅后即焚)·心跳/状态(脱离进程写,不进人读流)。
- 时刻:文件名与内文时刻先
date实取再落笔;估写=违规。 - 会话级活性判据:判对端活只认它的进度/回执/交回件 mtime;心跳/TICK/标记文件 由脱离进程写,只证进程活。停更超 40 分钟→探活件;探活 30 分钟无回执→备援。
- 收货门:交回件不是收货;主编排独立核对(数字回原文/关键宣称回源库面或真机/抽样复跑)后才收货;执行体降级时加码核对。引用他方数字必回原件逐字对;收件读全文,禁 tail 抽读后宣称「未落」;令件前提当刻 ls 确认。
- 台账:决策/事件台账是 SSOT(owner 原话逐字,事件按时刻前插);文件信箱件是过程,台账是结论。checkpoint/handoff 只记路径。
- 禁入文件信箱:凭据、密钥、明文口令(只写位置指针);签名尾注类平台默认物按项目铁律。
二、worktree 工作模式
- 一线一树:每条修复/功能线从钉死的基座 commit
git worktree add --detach <目录>/<线名> <sha>拉出;工单写明基座 sha,开工先rev-parse HEAD亲验。 - 改动面白名单+禁区写进工单;禁碰主线、发版树与他人树;合并权归主编排(cherry-pick/ff/tag 由编排做,线只 commit 不 push)。
- 禁
git stash:整仓所有 worktree 共享一个 stash 栈,并行线 pop 会互相弹错树(实证)。要证明测试会抓错,只用git show HEAD:<path>导出对比、单文件 checkout、或「改坏→红→复原→绿」。 - 写前自核:
git status --short,树上出现陌生 modified 文件=并发污染信号,停手上报,禁顺手 checkout 清掉(可能是别人唯一副本)。主编排解缠序:先双树全量 diff 快照,再git apply --check原子预检后搬运。 - 编号预分配:迁移号/工单号/端口由编排在派线时分配,防撞号;弃用的号留空不补。
- 跑批期树冻结:全量测试在某树上跑时禁改该树;并行封版另起 worktree 或等 DONE 标记文件。
- 清理:线并入且树净后
git worktree remove;发版 tag 落成后统一清;快照 patch 留 scratchpad 作证。 - 期望 commit 清单:合流后编排开列「线名→最终 SHA→来源注记」,构建方按清单核
git log集合相等+文件面同族——专治 stash 互踩后「tag 装错东西」。
三、角色速记
- 主编排:唯一汇合点与裁决者;发令、收货、合流、台账。
- 独立会话线(部署/复核/顾问):有自己的 Monitor 与心跳,靠文件信箱通讯,会话级活性按 §一.5 判。
- 子代理:由编排派出,交回件落文件信箱;换代后无法续聊,只能按交回件收货。
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.
- 2d ago First seen · 48 lines · 141 tokens per session scan A 6f6a5755ddb7
coordination-worktree is a skill published in the GitHub repository 0fuk/OpenACCP (2 stars, last pushed 2d ago), licensed MIT. It adds 141 tokens to every session and 1,871 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
commit
Git Commit Skill for creating well-structured, atomic commits following conventional-commits discipline.
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). The work commits land first, then the version bump, verification, and the release commit on top. Stops at "committed locally on main" — or, when the project releases…
oma-scm
Manage Git branches, merges, conflicts, commits, and release baselines. Use for repository history and change-management operations.
moai-ref-git-workflow
Git workflow patterns, branch strategies, conventional commits, and PR templates reference for git operations. Agent-extending skill that amplifies manager-git expertise with production-grade git workflow patterns. NOT for: code implementation, testing, architecture design, documentation content.
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
audit-trail
Full traceability from PRD to code commit through the CCPM spec-driven pipeline.