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/xcodethink/open-claude-code-skills/24npx skills add xcodethink/open-claude-code-skills --skill 24git clone --depth 1 https://github.com/xcodethink/open-claude-code-skillsWrote 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/xcodethink/open-claude-code-skills/24)<a href="https://agentmods.dev/skills/xcodethink/open-claude-code-skills/24"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/24.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 | $0.00274 | $0.03266 |
| Opus 5 | $0.00137 | $0.01633 |
| Sonnet 5 | $0.00055 | $0.00653 |
| Haiku 4.5 | $0.00027 | $0.00327 |
Grade A, and why
24-项目看板 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目看板 (Project Boards) v1.0
**起源 **: 要一套能像专业 PM 一样调度的本地看板 — 看全盘、钻单项目、知道下一步推哪个。
★ 设计铁律 (最高优先, 决定一切)
好看板必须锚在「垂直结构分解」(目标 ↓ 板块 ↓ 项) → 有分母、有边界、能完成。
- 禁止扁平「状态看板」 (Kanban 把 待办/进行中/阻塞/完成 当组织轴): 它没分母、待办列可无限加 → 制造 CLAUDE.md 最怕的「做不完的增项 / 无限优化循环 / 跑偏」, 是反 Scope-Lock (TEP) 的。
- 状态当「有界结构项的属性」 (格子颜色 / 角标), 不当组织轴。一个格子可以同时是「部分」+「下一步」, 用可叠加标记表达, 不用互斥状态。
- 试过扁平 Kanban, 已退役 (2026-06-09)。不要再提议扁平状态看板。
一个系统, 两层视图 (单一入口)
~/Developer/BOARD.html = 唯一入口 (不再一堆散页面/标签)。一个自包含 HTML, 内部路由:
| 视图 | 路由 | 锚在哪个垂直结构 (= 分母) |
|---|---|---|
| 全盘首页 | #/ |
项目 ↓ 项目 (扫 ~/Developer 全部 git 仓) — 点项目卡钻进去 |
| 项目详情 | #/p/<项目> |
项目 ↓ 板块 ↓ 模块 — 6 个 tab 分区 |
项目详情页 = 6 tab (不再一长条): 总揽(cockpit 板块网格+进度环) · 规划(现在做/下一步, 自动抽 focus/next+current-task) · 对话(conversation-log) · 提交(每天提交按天分组) · 部署(docs/releases) · 仓库(分支/P-1/未推/未提交改动/链接)。客户端切 tab, 不开新页。
统一口径: 全盘每个项目进度由系统从 cockpit 格子统一算 done/total (跨项目可比), 同时保留并标注项目自报目标 (如 ProjectA 自报)。解决"各项目理解有偏差导致维度不一样"。
板块格子: status 颜色 + 当前说明(meta) + 更新日期(该板块最近 git 提交) + 点开弹窗看实施历史(git log -- paths) + 对应文件。靠 cockpit 格子 paths 字段自动算, 零维护。
不开新标签: BOARD.html 路径固定, AI 重生后刷新已开的那个标签 (Cmd+R) 即可, 不要每次 open 开新标签。
目录结构
24-项目看板/
├── SKILL.md # 本文件
├── system/ # ★ 看板系统 (单一入口, 日常用这个)
│ ├── board-system.mjs # 生成器: 扫所有项目 + bundle cockpit + 统一算 → BOARD.html
│ ├── board-system.template.html # 单页 app (路由: 全盘 ⇄ 项目)
│ └── board-run.sh # launchd 周任务 wrapper (显式 source nvm)
└── cockpit/ # 单项目 cockpit 引擎 (被系统复用 + 项目内 npm run cockpit)
├── cockpit-visual.template.html # 通用模板 (自渲染, 别手改, 改数据)
├── render-cockpit.mjs # 零依赖生成器 (--adopt / --sync / --init / --validate)
├── cockpit.data.schema.json # 数据格式 (字段说明都在里面)
├── cockpit.data.example.json # 可照抄的范例
└── README.md # cockpit 详细说明
用法
项目级 cockpit (单项目进度)
一键接入 (新项目用这个) — 在项目根目录跑一条命令, 自动 copy 工具到 scripts/cockpit/ + 加 npm run cockpit 脚本 + 起 docs/cockpit.json 骨架 + 生成 docs/cockpit.html:
cd <项目根>
node ~/.claude/skills/24-项目看板/cockpit/render-cockpit.mjs --adopt
# 或显式指定: node .../render-cockpit.mjs --adopt /path/to/项目
接入后: 编辑 docs/cockpit.json 填真实模块结构(分母 — 命令装不了, 这是判断活) → npm run cockpit 重生。
模板/生成器升级后, 刷新某项目的副本: node .../render-cockpit.mjs --sync <项目>。
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- cockpit/cockpit-visual.template.html 12 KB
- cockpit/cockpit.data.example.json 2.6 KB
- cockpit/cockpit.data.schema.json 6.0 KB
- cockpit/README.md 4.6 KB
- cockpit/render-cockpit.mjs 8.9 KB runs code
- SKILL.en.md 12 KB
- system/board-run.sh 420 B runs code
- system/board-system.mjs 17 KB runs code
- system/board-system.template.html 19 KB
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 · 127 lines · 274 tokens per session scan A 1adbcbc7c247
24-项目看板 is a skill published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 29d ago), licensed MIT. It adds 274 tokens to every session and 3,266 once invoked, about $0.0014 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
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
agent-phase-closeout
中文阶段收尾技能。用于完成一个阶段、准备开新对话、需要更新状态快照、冻结模块、整理已完成任务和下一步任务时。触发语包括"阶段收尾""帮我收工""准备开新对话""更新快照""冻结阶段""总结当前状态"。.
orchestrate
Pipeline orchestration: dispatch the highest-priority ready tasks/work units to agents, manage capacity, and coordinate the Todo to Done flow. Invoked as /agiflow:orchestrate. Uses listtasks, listactivetasksbyorg, listmembers, updatetask, getworkunitprogress.
moai-workflow-project
Integrated project management system covering documentation, language initialization, template optimization, docs generation, and JIT document loading. Absorbed from moai-workflow-templates, moai-docs-generation, and moai-workflow-jit-docs.
backlog-grooming
Review Agiflow Planning tasks for readiness, prioritize approved work, group related tasks into work units, and promote ready tasks to Todo. Use when grooming a backlog, organizing planned tasks, creating work units, or deciding what should be executed next.
project-plan
Turn a product goal or feature request into a clear Agiflow project plan with small, testable tasks in Planning status. Use when starting a project, decomposing a feature, clarifying requirements, or converting an idea into an actionable backlog.