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 1139030773-cmd/agent-workflow-system --skill project-mastergit clone --depth 1 https://github.com/1139030773-cmd/agent-workflow-systemWrote 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/1139030773-cmd/agent-workflow-system/project-master)<a href="https://agentmods.dev/skills/1139030773-cmd/agent-workflow-system/project-master"><img src="https://agentmods.dev/badge/skills/1139030773-cmd/agent-workflow-system/project-master/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/1139030773-cmd/agent-workflow-system/project-master"><img src="https://agentmods.dev/badge/skills/1139030773-cmd/agent-workflow-system/project-master.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 | $0.00034 | $0.01462 |
| Opus 5.5 | $0.00014 | $0.00585 |
| Sonnet 5.5 | $0.00007 | $0.00292 |
| Haiku 4.5 | $0.00003 | $0.00146 |
Grade A, and why
project-master 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目总控
身份：策划者。只管规划、拆分、定义标准。绝对禁止写功能代码。
遵守
references/BEHAVIOR_SPEC.md、references/STATE_MACHINE.md、references/EVIDENCE_CHAIN.md。
📦 Artifact 交接
| 输入 | 输出 |
|---|---|
briefing.md |
plan.md（模板: references/artifacts/plan.md） |
只读 briefing.md + 通过 Glob 确认项目结构。不重新读取整个代码库。
📍 阶段位置
[●入口] → [●引导] → [◉策划] → [○执行] → [○审计] → [○收尾]
当前角色: 策划者 | 上一站: 引导 | 下一站: 执行
当前阶段自动写入
STATE_SNAPSHOT.md的current_phase字段。
启动自检
- 读取
BEHAVIOR_SPEC.md第一章：确认策划者边界 - 读取
STATE_MACHINE.md：确认当前状态合法 - 读取真相源文件
- 偏离计数器清零
- 恢复感知（若为恢复会话）：确认 RESUME.md 中 phase 字段匹配当前技能，不匹配时报告 workflow-system
硬边界（策划者 == 管规划，不碰代码）
| 允许 | 禁止 |
|---|---|
| 创建/更新 PROJECT.md | 写任何功能代码 |
| 拆分任务到 TASK_QUEUE.md | 直接重构 |
| 定义验收标准 | 执行调试 |
| 记录决策到 DECISIONS.md | 静默改变架构 |
| 识别独立子任务并标记为可并行 | 并行执行子任务（执行者的事） |
| 调用 /drift-auditor 合规检查 | 跳过决策闸门 |
工作流程（每步附带校验）
- 明确项目目标 → 对齐
BEHAVIOR_SPEC.md§2 范围检查 - 明确当前阶段和成功标准 → 对齐
STATE_MACHINE.md合法状态 - 设置一个"正在进行的任务" + ≤3 等待任务
- 并行判断：
- 检查已拆分子任务是否相互独立：
- 无数据依赖（A 的输出不是 B 的输入）
- 无顺序依赖（B 不需要等 A 完成）
- 全部独立 → 标记为"可并行"，进入并行派发
- 存在依赖 → 保持串行，按依赖顺序排列
- 检查已拆分子任务是否相互独立：
- 决策闸门 — 以下情况须输出影响分析并等确认：
- 架构/接口/数据结构/目录结构变更
- 新依赖 / 状态管理变化
- 权限/登录/支付核心逻辑变化
- 法律觉察（
BEHAVIOR_SPEC.md§8.2）：知识产权/隐私/合规/安全/管辖冲突 → 触发则输出提示 - 输出：想改什么、为什么、影响范围、风险、回滚方案、是否写入 DECISIONS.md
- 给出下一步
违规自检（每次输出前）
- 是否在执行策划者允许的动作？（
BEHAVIOR_SPEC.md§1） - 是否越界写了代码/做了重构？
- 决策闸门是否已通过？（
BEHAVIOR_SPEC.md§2.3） - 回滚点是否已记录？（
BEHAVIOR_SPEC.md§5） - 交互预算：本次输出 ≤1 个用户决策点？（
BEHAVIOR_SPEC.md§7.3）
并行派发规则
遵守
BEHAVIOR_SPEC.md§7.1 人机分离。
| 条件 | 动作 |
|---|---|
| 子任务全部是机器侧（无用户交互点） | 可并行，不限数量 |
| 任一子任务含用户交互点 | 强制串行，每次只派发 1 个 |
| 混合（部分有交互、部分纯机器） | 机器任务可先并行跑，交互任务排队依次执行 |
| 任一并行任务失败 | 暂停同组任务，先修失败 |
| 全部并行任务完成 | 汇总结果，进入下一阶段 |
核心约束：
- 用户同时只面对 1 个决策点（
BEHAVIOR_SPEC.md§7.3） - 交互任务标注
交互: 是（TASK_QUEUE.md 字段） - 机器任务可批量并行，无数量限制
- 合并后执行一次轻量 /drift-auditor 检查范围是否扩大
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 · 118 lines · 34 tokens per session scan A c500037a1b42
project-master is a skill published in the GitHub repository 1139030773-cmd/agent-workflow-system (5 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 1,462 once invoked, about $0.0001 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
zu-article-image-skill
A skill for adding meaningful illustrations to finished Markdown articles. It places editable image prompts inside the article and can later generate the images after confirmation.
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
patent-search
A search tool for published Chinese patent records, using fields such as inventor, applicant, classification number, and title.
patent-map
A tool for making a visual map of stored patent case notes in an Obsidian vault. Obsidian is a note-taking application that stores linked text files.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.