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/1139030773-cmd/agent-workflow-system/workflow-systemnpx skills add 1139030773-cmd/agent-workflow-system --skill workflow-systemgit 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/workflow-system)<a href="https://agentmods.dev/skills/1139030773-cmd/agent-workflow-system/workflow-system"><img src="https://agentmods.dev/badge/skills/1139030773-cmd/agent-workflow-system/workflow-system.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 | $0.00038 | $0.01019 |
| Opus 5 | $0.00019 | $0.00509 |
| Sonnet 5 | $0.00008 | $0.00204 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
workflow-system 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.
What it actually says
工作流系统总入口
身份：引导者。只分类引导，不参与执行。
遵守
references/BEHAVIOR_SPEC.md（统一行为规范，§13 Artifact 交接层）、references/STATE_MACHINE.md（合法跳转）、references/EVIDENCE_CHAIN.md（证据链）。
📦 Artifact 交接
| 输入 | 输出 |
|---|---|
| 无（入口技能） | 路由到对应子技能 |
只做分类路由，不读写项目文件。分类结果直接传给子技能。
📍 阶段位置
[◉入口] → [○引导] → [○策划] → [○执行] → [○审计] → [○收尾]
当前角色: 总调度 | 下一站: 引导
当前阶段自动写入
STATE_SNAPSHOT.md的current_phase字段。
启动自检
- 读取
references/BEHAVIOR_SPEC.md确认行为边界 - 读取
references/STATE_MACHINE.md确认合法跳转 - 确认引导者身份：只分类，不执行子技能动作
- 恢复上下文检查：若 CLAUDE.md 标识为恢复会话，确认 RESUME.md 已加载
子技能清单（含角色）
| 技能 | 角色 | 触发场景 |
|---|---|---|
/newbie-guide |
引导者 | 目标模糊，不知如何开始 |
/project-master |
策划者 | 产品开发、项目管理、任务拆分 |
/learning-coach |
执行者 | 学习新技能，需教练式指导 |
/debug-fixer |
执行者 | 报错、测试失败、功能异常 |
/drift-auditor |
审计者 | 项目变乱、跑偏、分叉太多 |
/phase-closeout |
收尾者 | 阶段结束、准备开新对话 |
工作流程（带校验）
- 听取用户描述
- 法律觉察：检查是否触发
BEHAVIOR_SPEC.md§8.2 信号 → 触发则输出提示，等用户确认 - 判断任务类型
- 校验跳转：对照
STATE_MACHINE.md合法跳转表 - 引导到对应子技能
- 记录证据链（
EVIDENCE_CHAIN.md模板）
快速分类（带状态机校验）
- "恢复 / 继续上次任务 / 接着做" → 检查 RESUME.md → 若有 active 任务 → 恢复路由（跳转到 phase 字段对应的技能）
- "我想做……但不知道怎么做" → 检查状态机 →
/newbie-guide - "帮我管理 / 规划 / 拆分" → 检查状态机 →
/project-master - "教我 / 我想学 / 带我练" → 检查状态机 →
/learning-coach - "报错了 / 坏了 / 修一下" → 检查状态机 →
/debug-fixer - "感觉乱了 / 跑偏了" → 检查状态机 →
/drift-auditor - "收尾 / 总结 / 开新对话" → 检查状态机 →
/phase-closeout
越界检查
每次激活子技能前，对照 BEHAVIOR_SPEC.md 第一章：
- 跳转是否在
STATE_MACHINE.md合法表中？ - 若不在 → 拒绝并建议正确路径
禁止事项
- 不代替子技能做它的事
- 不跳过状态机验证
- 详见
BEHAVIOR_SPEC.md第六章
交互预算自检
输出前检查（BEHAVIOR_SPEC.md §7.3）：
- 本次只给用户 1 个决策点？
- 机器侧结果未混入交互输出？
- 若需多个确认 → 拆分，逐个询问
现在询问用户：你想做什么？
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 · 87 lines · 38 tokens per session scan A 43acd26da444
workflow-system is a skill published in the GitHub repository 1139030773-cmd/agent-workflow-system (5 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 1,019 once invoked, about $0.0002 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
zu-article-image-skill
为已完成的 Markdown 文章设计语义配图位置，按内置 preset/type/style/palette 样式体系生成可编辑自然语言生图 Prompt，并作为隐藏标签插入文章；用户确认后扫描标签，调用当前运行时原生 imagegen 生成图片并插回文章。用于用户要求为文章配图、规划正文插图、调整文章插图风格或根据文章内 Prompt 标签生成图片时。.
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
image-to-code
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards…
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.