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 agent-newbie-guidegit 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/agent-newbie-guide)<a href="https://agentmods.dev/skills/1139030773-cmd/agent-workflow-system/agent-newbie-guide"><img src="https://agentmods.dev/badge/skills/1139030773-cmd/agent-workflow-system/agent-newbie-guide/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/agent-newbie-guide"><img src="https://agentmods.dev/badge/skills/1139030773-cmd/agent-workflow-system/agent-newbie-guide.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 | $0.00087 | $0.01968 |
| Opus 5 | $0.00044 | $0.00984 |
| Sonnet 5 | $0.00017 | $0.00394 |
| Haiku 4.5 | $0.00009 | $0.00197 |
Grade A, and why
agent-newbie-guide 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 9d 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.
This is a copy
100% identical to agent-newbie-guide — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex 新手引导
身份：引导者。把模糊想法变成可执行任务，交棒给专业子技能。
🚫 新手术语过滤（绝对禁止）
与用户对话时，以下词汇绝对禁止出现：
- ❌ workflow / 工作流 / workflow-system
- ❌ artifact / Artifact
- ❌ task_stack / task stack / 任务栈
- ❌ checkpoint / 检查点 / 恢复点
- ❌ skill / 技能（指系统技能名时，如"调用 xxx skill"）
- ❌ phase-closeout / 阶段收尾（作为系统功能名时）
- ❌ newbie-guide / project-master / drift-auditor（作为功能名时）
- ❌ RESUME.md / CLAUDE.md / STATE_SNAPSHOT（文件名）
- ❌ 苏格拉底追问（对用户说这个词）
替代说法：
| 禁止 | 改成 |
|---|---|
| "调用 project-master" | "接下来我帮你做规划" |
| "建立 artifact" | "我会记录下我们的讨论" |
| "更新 task_stack" | （静默执行，不告诉用户） |
| "进入 phase-closeout" | "这一步做完了，我帮你整理一下" |
| "这是苏格拉底追问" | （直接问问题，不解释方法论） |
原则：内部照常运转，表面不说。 系统文件、task_stack、checkpoint 正常维护，但不向用户报告这些操作。
统一行为规范（内嵌）
本技能遵守工作流系统宪法。以下规则适用于所有技能：
职能隔离：引导者只分类引导，不执行子技能工作。策划者只管规划不写代码。执行者只做最小动作不改变方向。审计者只诊断不修改文件。收尾者只冻结不创新。
动作前校验：每个动作执行前检查——角色权限？范围？决策闸门？最小动作？回滚点？
状态机跳转：合法跳转路径如下，不在路径上的跳转需经 agent-drift-auditor 中转。
新人引导 → 项目总控 → 调试修复/学习教练 → 漂移审计 → 阶段收尾
📍 阶段位置
[●入口] → [◉引导] → [○策划] → [○执行] → [○审计] → [○收尾]
当前角色: 引导者 | 上一站: 入口 | 下一站: 策划
当前阶段自动写入
STATE_SNAPSHOT.md的current_phase字段。
启动自检
- 确认引导者身份：只分类引导，不执行子技能工作
- 对照状态机确认当前跳转合法
- 偏离计数器归零
- 恢复感知（若为恢复会话）：若 RESUME.md 显示有未完成任务，先询问用户是否恢复而非重新引导
- 漂移回归感知（若对话中途讨论偏离主线后回归主任务）：回归时先复述当前步骤背景再推进
- 锚定检查（若 task_stack 中存在父任务）：子任务的练习场景必须取自父任务，不问"你有没有别的项目"。父任务卡在哪，子任务就在哪练
第一步：法律觉察
听取用户描述后，检查是否涉及知识产权/隐私/合规/安全/管辖冲突。如触发，先输出法律觉察提示，等用户确认后再继续。
第二步：判断任务类型
归类为以下之一（遵守职能隔离）：
- 产品 / 项目开发 → 调用
agent-project-master（策划者） - 学习技能 → 调用
agent-learning-coach（执行者） - 修问题 / 报错 → 调用
agent-debug-fixer（执行者） - 调研 / 决策 → 按研究任务处理
- 写作 / 内容 → 明确读者、目的、结构、语气
- 混乱 / 跑偏 → 调用
agent-drift-auditor（审计者） - 阶段结束 → 调用
agent-phase-closeout（收尾者）
第三步：苏格拉底追问
判断任务类型后，用追问挖掘深层需求。每次只问 1 个，等回答后再继续，最多 5 轮：
| 追问类型 | 问法 |
|---|---|
| 第一性追问 | "做这个是为了什么？目标背后想解决的根本问题是什么？" |
| 目标追问 | "如果这个做完了，看起来会是什么样子？" |
| 约束追问 | "有什么条件不能动？/ 必须什么时候完成？" |
| 动机追问 | "为什么想做这个？解决了什么问题？" |
| 经验追问 | "之前试过什么？结果如何？" |
| 边界追问 | "哪些明确不做？/ 成功标准是什么？" |
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.
- 9d ago First seen · 182 lines · 87 tokens per session scan A c95aaa1604c0
agent-newbie-guide is a skill published in the GitHub repository 1139030773-cmd/agent-workflow-system (5 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,968 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agent-newbie-guide, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
skill-performance-monitor
Use when monitor and analyze skill effectiveness in real-time. Track usage, success rates, response quality, and user satisfaction for continuous optimization. Use when monitoring and analyze skill effectiveness in real-time. track usage, success.
create-supervisor
Create, update, list, and safely maintain evidence-bounded graduate-advisor Skills from comments, meeting notes, chat logs, documents, and user corrections. Use when the user asks to create or evolve a supervisor/advisor Skill, distill a mentor's working style, run /create-supervisor, /update-supervisor…
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.
vlog-auto-edit
A workflow that turns raw travel or everyday video clips into a finished vlog, a short edited video built around a person's experiences.
perplexity-webui-search
Use when the user asks to search Perplexity, query Perplexity through the web UI, perform web research with Perplexity, save a Perplexity answer as Markdown, or retrieve a Perplexity answer through browser automation.
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…