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 xcodethink/open-claude-code-skills --skill 21git 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/21)<a href="https://agentmods.dev/skills/xcodethink/open-claude-code-skills/21"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/21/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/xcodethink/open-claude-code-skills/21"><img src="https://agentmods.dev/badge/skills/xcodethink/open-claude-code-skills/21.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 | $0.00212 | $0.03446 |
| Opus 5.5 | $0.00085 | $0.01378 |
| Sonnet 5.5 | $0.00042 | $0.00689 |
| Haiku 4.5 | $0.00021 | $0.00345 |
Grade A, and why
21-任务执行纪律 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 1mo 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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Execution Protocol (TEP) v1.0
解决的问题: AI 开发过程中 (1) 功能遗漏/跳过 (2) 升级到一半跑偏 (3) 陷入无限优化循环。 灵感来源: Google Design Doc scope lock + Microsoft Definition of Done + Agile Sprint Boundary。 生效范围: 每个任务，每次对话，自动生效。用户不需要说"按 TEP 走"。
第一原则: 范围即合同
用户说的每一句任务指令 = 一份合同。合同外的工作 = 越权。 "一次做到位" 指的是 把合同内的事做到极致，不是 自己加条款。
Phase 0: 范围锁定 (Scope Lock) — 动手前必做
收到任务后，第一件事输出 Scope Card:
[Scope Card]
任务: [用户原话，不改写]
交付物: [具体要交付什么，用编号列表]
1. ...
2. ...
3. ...
不做: [明确排除什么 — 至少列 1 条]
完成标志: [怎么判断做完了 — 必须是可验证的]
预估改动: [约 N 个文件 / N 行]
Scope Card 规则:
- 交付物必须可数 — "优化性能" 不合格，"API 响应时间从 3s 降到 1s" 合格
- 不做清单必须写 — 强制思考边界，防止自己偷偷扩大范围
- 用户未确认前可以开始小任务 — 但大任务 (预估 ≥ 5 文件) 必须等用户确认 Scope Card
- Scope Card 写完就锁定 — 后续所有工作必须对照 Scope Card，不在卡上的不做
短任务简化版 (预估 ≤ 2 文件):
[Scope] 改 X 文件的 Y 功能。不动 Z。完成 = 测试通过。
Phase 1: 拆解与追踪 (Task Breakdown) — TodoWrite 强制使用
规则:
- 任何任务 ≥ 3 步 → 必须用 TodoWrite 拆解
- 每个 todo item 必须对应 Scope Card 的某个交付物
- 禁止出现 Scope Card 之外的 todo item — 发现需要额外工作 → 走 Phase 3 (范围变更)
- 每完成 1 个 item → 立即标 completed → 检查是否对齐 Scope Card
- 最后一个 item 必须是 "验收: 对照 Scope Card 逐条确认"
Todo Item 命名规则:
好: "实现用户注册 API endpoint"
坏: "优化代码" (太模糊，容易变成无底洞)
好: "修复登录页 403 错误"
坏: "改进登录体验" (没有边界)
Phase 2: 执行纪律 (Execution Discipline) — 写代码时的硬约束
2.1 单轨执行 (Single Track)
- 一次只做一个 todo item — 不并行，不跳跃
- 当前 item 没标 completed 之前，不开始下一个
- 如果当前 item 受阻 → 记录阻塞原因 → 问用户 → 不自己绕路做别的
2.2 范围边界巡逻 (Scope Patrol) — 每写 1 个文件后自问:
这个改动在 Scope Card 上吗?
是 → 继续
否 → STOP. 走 Phase 3.
2.3 深度陷阱检测 (Depth Trap Detection)
AI 在执行中必须监控以下信号，任何一个触发 → 立即暂停:
| 信号 | 含义 | 动作 |
|---|---|---|
| 同一个模块连续改 ≥ 3 个文件且不在 Scope Card 上 | 正在陷入优化循环 | STOP + 报告用户 |
| 发现"顺便可以改进"的地方 ≥ 2 处 | 正在 scope creep | 记录到 Parking Lot，不动手 |
| 当前 todo item 拆出了 ≥ 3 个子步骤 | item 粒度太粗，或正在膨胀 | 重新拆解，不继续埋头做 |
| 已经改了 ≥ 10 个文件但 Scope Card 预估 ≤ 5 | 严重超出预期 | STOP + 向用户报告偏差 |
| 做了 ≥ 30 分钟 (估算) 但第 1 个交付物还没完成 | 可能卡在了细节里 | 自检 + 报告进度 |
2.4 Parking Lot (停车场) — 不丢失但不立刻做
执行中发现的"好想法"、"顺便优化"、"也应该改"的事情:
[Parking Lot]
- [ ] 发现: X 模块的 Y 也需要类似改动 (来源: 做 Scope #2 时发现)
- [ ] 发现: Z 函数命名不一致 (来源: 读代码时注意到)
- Parking Lot 在任务结束时一次性报给用户
- 用户说"做" → 变成新的 Scope Card
- 用户说"不做" → 归档
- 绝对不允许在执行中偷偷从 Parking Lot 里拿东西出来做
What ships with it
4 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.
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.
- 1mo ago First seen · 246 lines · 212 tokens per session scan A 16148645ee6f
21-任务执行纪律 is a skill published in the GitHub repository xcodethink/open-claude-code-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 212 tokens to every session and 3,446 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
requirements-writer
Use when converting PM intake into a slice SPEC.md with observable acceptance outcomes, explicit scope, and advisory sibling build dependencies.
batch-all-issues
Resolve every open issue one at a time: fact-check each with web research, close the ones that need no action, and run the goal-pr skill to fix, review, and merge the ones that do — repeating until no actionable issues remain.
post-issue-comment
Post a reply comment on a GitHub issue in English with a natural, concise writing style, based on the intent passed as arguments.
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.
ticket-craft
Create Jira/Asana/Linear tickets optimized for Claude Code execution - AI-native ticket writing.
brainstorm-feature
SDLC intake that turns a rough idea into an approved BRD-lite brief (Why lane) or delivery contract (Direction lane) at docs/brd/brd-[slug].md, sized by SNC tier.