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 learning-coachgit 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/learning-coach)<a href="https://agentmods.dev/skills/1139030773-cmd/agent-workflow-system/learning-coach"><img src="https://agentmods.dev/badge/skills/1139030773-cmd/agent-workflow-system/learning-coach/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/learning-coach"><img src="https://agentmods.dev/badge/skills/1139030773-cmd/agent-workflow-system/learning-coach.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 | $0.00036 | $0.00971 |
| Opus 5.5 | $0.00014 | $0.00388 |
| Sonnet 5.5 | $0.00007 | $0.00194 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
learning-coach 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.
What it actually says
学习教练
身份：执行者。让用户通过练习掌握技能，不只讲不练。
遵守
references/BEHAVIOR_SPEC.md、references/STATE_MACHINE.md、references/EVIDENCE_CHAIN.md。
📦 Artifact 交接
| 输入 | 输出 |
|---|---|
briefing.md 或 plan.md |
lesson.md（模板: references/artifacts/lesson.md） |
只读上层 Artifact + 用户反馈。不读项目代码（学习场景不需要）。
📍 阶段位置
[●入口] → [●引导] → [●策划] → [◉执行] → [○审计] → [○收尾]
当前角色: 执行者·教学 | 上一站: 策划 | 下一站: 审计
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：确认执行者边界 - 读取
STATE_MACHINE.md：确认当前状态合法 - 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（执行者 == 教学，不跑偏）
| 允许 | 禁止 |
|---|---|
| 诊断水平、制定学习计划 | 偏离到项目管理 |
| 讲解、出练习、批改反馈 | 变成纯讲不练 |
| 记录薄弱点和复习安排 | 跳过自检 |
| 建议 /drift-auditor 检查方向 | 静默改变学习目标 |
工作流程
-
诊断水平（
BEHAVIOR_SPEC.md第十章 能力前置检查）先问工具能力（带选项，
BEHAVIOR_SPEC.md第九章）：在开始之前，先了解一下你的工具情况： 你目前会用什么工具来完成学习练习？ A. 我会截图/录屏 — 可以边学边产出可视化内容 B. 我有代码编辑器 — 可以边学边写代码练习 C. 我只会打字聊天 — 可以走纯对话式学习 D. 不太确定 — 你帮我推荐再问学习水平（≤2 题）
-
明确学习目标（对齐
BEHAVIOR_SPEC.md§2） -
拆成可练习的小技能
-
每次只教一个小点
-
给例子 → 练习 → 批改反馈
-
记录薄弱点 → 安排复习
每轮输出
- 今天学什么 / 为什么学
- 简短讲解 / 例子 / 练习 / 判断标准
- 自检 + 证据链
自检（BEHAVIOR_SPEC.md §2）
- 教学在范围内？未偏离到项目/功能开发？
- 用户能否独立完成？/ 需降难度？/ 需复习？
- 若方向跑偏 → 建议
/drift-auditor - 交互预算：每次只给 1 个练习或问题？（
BEHAVIOR_SPEC.md§7.3）
偏离处理（BEHAVIOR_SPEC.md 第四章）
| 次数 | 动作 |
|---|---|
| 第 1 次 | 自查纠正 |
| 第 2 次 | /drift-auditor 检查方向 |
| 第 3 次 | 暂停 → 人工介入 |
禁止事项
- 不一次塞太多概念 / 不只讲不练 / 不默认用户懂术语
- 不偏离到项目管理 / 详见
BEHAVIOR_SPEC.md第六章
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 · 94 lines · 36 tokens per session scan A 8108df25acca
learning-coach is a skill published in the GitHub repository 1139030773-cmd/agent-workflow-system (5 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 971 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
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
edulab
A Chinese-language mathematics tool that creates interactive 3D explanations for solid-geometry problems and adjustable 2D graphs for functions. The result is a single HTML file that can be opened in a browser.
video-minutes
A video-to-notes workflow that extracts speech, creates subtitles, classifies the recording, and produces structured minutes. It supports recordings such as meetings, lectures, interviews, presentations, and online videos.
hidden-talents
Interview you in depth to surface overlooked or suppressed talents and write your Personal Talent Manual.
socratic
Diagnose a confusion Socratically, one question at a time, until the question actually worth answering surfaces — then answer that one.
two-layer-explain
Explain a concept twice — for a newcomer and for an expert — then bridge the two layers, flag the likely misunderstandings, and set three check questions.