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 rebootgit 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/reboot)<a href="https://agentmods.dev/skills/0fuk/openaccp/reboot"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/reboot/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/reboot"><img src="https://agentmods.dev/badge/skills/0fuk/openaccp/reboot.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 | $0.00162 | $0.02120 |
| Opus 5.5 | $0.00065 | $0.00848 |
| Sonnet 5.5 | $0.00032 | $0.00424 |
| Haiku 4.5 | $0.00016 | $0.00212 |
Grade A, and why
reboot 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/reboot — 主编排换代接力(项目无关引擎)
目的:把主编排指挥权完整交给一个全新会话——自包含交接文档(零背景粘贴即接管)+所有 lane 闭环指向新任(播报→握手→回执核销→旧地址清扫,缺一不算完成)。项目事实读项目根 PROJECT-PROFILE.md(registry/协调目录/台账/命名惯例);没有就走 §0 发现,并在首次成功后把发现结果写进该项目的 PROFILE。
原则
- skill 零项目事实;实时态 实测重抓,沉淀态 从上一份 handoff 沿用刷新。
- 握手要闭环:播报≠完成;未回执=未接通,升级 owner。
- 失效路径=交接杀手:生成后逐路径验存在。零密钥零 PII,凭据只写位置指针。
- 交接件≠决策全集:从上一份 handoff 沿用=复利丢项。owner 决策 backlog 必须对照常设决策台账重建;「已裁未派工」最易蒸发(不在「未决」也不在「在飞」),单列必查。
- 回归门≠完成门:凡「全绿/完成/验收」字样必须并排决策完成度四态(已合流/在飞/已裁未派工/候 owner)。
步骤 0 · 定位项目(禁猜)
①当前会话上下文 → ②项目 PROFILE / 记忆索引 → ③Glob 种子(**/coordination/*registry*.json、**/*handoff*.md、**/*RESTART_PROMPT*.md)→ ④全找不到问 owner 一次。代号沿用项目惯例(有 G{n} 用 G{n+1});首代用 <项目>-ORCH-HANDOFF-<日期>-001.md。
- 退化:单会话项目=握手空跑;非 git 生产区=跳过 git 快照并注明。
- 同代重启(owner 明示 G{n}→G{n}):代号不变,文件名
*-G{n}-SELF-RESTART-handoff-*;各线握手可豁免(心跳/回执 30 分钟内=链路活,只发轻量知会);其余步骤一步不少。
步骤 1 · 实时态 快照(全实测)
①各线地址+isRunning(标「快照,接管者必复核」);②各生产区 git head+local vs origin(落后且干净→先推闭合备份缺口;WIP 只记录);③协调目录 ls -t 最新交付物+项目健康计数;④未决请裁汇总(各线问了没答的);⑤后台残留盘点:在飞子代理/Monitor/后台命令逐一列——旧会话派出的子代理换代后无法续聊,只能按其交回件收货,记「孤儿+交回件路径+预计落地+是否需重派」;⑥叫醒机制实证表:每个叫醒机制最近真触发时刻+证据文件,零触发的标死。
步骤 2 · 沉淀态 汇编(读权威源)
上一份 handoff 为骨架刷新;lane registry 为 lane 权威;本代裁决/verdict 指针列表;owner 长期指令汇编(registry AMEND/记忆 feedback/上一份铁律节,逐条带出处,新任生来携带);owner 待办携带(含默认值口径);决策完成度台账(定位常设台账,没有=先建再交;四态计数;「已裁未派工」清单全文列入,禁只给指针);owner 验收口径逐字(接任者无权重新解释);编号命名空间表(多套编号曾撞车的项目必带)。
步骤 3 · 写 handoff(骨架;[V]=实测,[D]=沿用刷新)
# <项目> 主编排 <前任>→<新任> 换代接力交接(<时间戳>)
> owner:新会话整段粘这份即接管为 G{n+1}(主循环模型=<项目铁律>)。换代根因=<原因>。
§0 接管立即做:①确认模型合规+加载项目 skill ①.5 必读文档清单(每份一句为什么必读;读完才许派单;**走五门发版范式的项目首项固定=现役五门台账(最新工单集),先答「本车在哪一门、哪些卡缺哪一门」再读其余**)②复核各线地址 ③向各活线播接管+握手 ④握手台账(播报/通道/回执/文件;全线回执才算完成;超时未回执列名单请 owner 重开)⑤旧地址清扫(grep 各线台账/boot 里前任地址改指新任)⑥重架 Monitor(v4,定时唤醒兜底)+回扫「快照时刻→Monitor 基线时刻」漏件 ⑦更新 registry 现任与裁决权字段 ⑧接管 24 小时对账义务(独立重建 owner backlog 与主线现状 diff,差异呈 owner)⑨依赖拆解检查(阻塞队列内零依赖项立即拆出并行)
§1 你是谁 [D](含本 skill 自指) §2 各线实时态 [V] §3 已闭合裁决 [V] §3.5 未决请裁 [V] §3.6 决策完成度核算 [V](已裁未派工全文) §3.7 owner 验收口径 [D] §4-§6 事实源/生产区/业务底座 [D] §7 环境坑+叫醒机制实证表 [V] §8 通信协议+寻址铁律 [D] §9 铁律+owner 长期指令汇编 [D] §9.5 owner 待办 [V] §10 不做+项目间隔离 [D] §11 后台残留(孤儿子代理与其交回件路径) [V]
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 · 47 lines · 162 tokens per session scan A 3359374d1b44
reboot is a skill published in the GitHub repository 0fuk/OpenACCP (2 stars, last pushed 2d ago), licensed MIT. It adds 162 tokens to every session and 2,120 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
handoff-mesh
Built-in communication layer for multi-agent setups. Full-mesh handoff folders (any agent can hand off to any other), an hourly watcher that surfaces open handoffs, weekly archive cleanup, and a completion-reporting loop so every handoff is handled AND verified. The durable 'brain' counterpart to real-time channels…
agent-teams
Coordinates Claude agent teams via filesystem protocol. Use when orchestrating parallel agents with task dependencies. Do not use for single-agent tasks.
orchestrate
This skill should be used when the user asks to 'orchestrate a task', 'break down work into parallel agents', 'coordinate subtasks', 'run agents in parallel', or mentions 'multi-agent'. Decomposes complex tasks into tracked subtasks, dispatches parallel subagents, and coordinates until completion.
silicon-steward
A planning guide for coordinating work between a person and a coding agent. It turns required information, resources, feedback, actions, and handoffs into explicit checklists and protocols.
coordinate-recover
Diagnose and safely resume Coordinate Agents Tasks after executable failure, non-zero exit, timeout, stale claim, processing message, or Implementer ERROR. Recovery is explicit and never an automatic retry loop.
coordinate-setup
Discover or configure implementation agents for Coordinate Agents when setting up or changing its agent configuration.