24-项目看板

24-项目看板 is a skill for Claude Code, Codex from xcodethink/open-claude-code-skills. It costs 274 tokens per session (3,266 once invoked), scanned A, original, MIT.

A local project dashboard that shows progress across Git repositories and lets you open a detailed view for each project. It uses a structured breakdown of goals, sections, and modules instead of a flat task board.

In plain words
What is it for?
Use it to review many projects, inspect one project’s progress, track commits and changes, organize modules, and identify what should happen next.
Why use it?
It gives projects a shared measure of progress, current work, next steps, repository activity, deployments, and implementation history in one place.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/xcodethink/open-claude-code-skills/24
Any agent
npx skills add xcodethink/open-claude-code-skills --skill 24
Clone the repo
git clone --depth 1 https://github.com/xcodethink/open-claude-code-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for 24-项目看板

README.md
[![agentmods](https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/24.svg)](https://agentmods.dev/skills/xcodethink/open-claude-code-skills/24)
Your own site
<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>
Per session 274 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,266 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash 1adbcbc7c247, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 3 executable files (cockpit/render-cockpit.mjs, system/board-run.sh, system/board-system.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/24-项目看板/SKILL.md · 127 lines

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>

Read the full file on GitHub · 127 lines

Changes

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.

  1. 4d ago First seen · 127 lines · 274 tokens per session scan A 1adbcbc7c247

Subscribe to this mod's changes

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.

Related

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…

modu-ai/moai-adk · 76 tokens

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"。.

hashgraph-online/awesome-codex-plugins · 73 tokens

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.

hashgraph-online/awesome-codex-plugins · 64 tokens

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.

modu-ai/moai-adk · 55 tokens

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.

hashgraph-online/awesome-codex-plugins · 55 tokens

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.

hashgraph-online/awesome-codex-plugins · 52 tokens