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 commands/awesome-embedded-learning-studio/tutorial_awesomemoderncpp/patchgit clone --depth 1 https://github.com/Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPPWhat 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 | $0.00044 | $0.01024 |
| Opus 5 | $0.00022 | $0.00512 |
| Sonnet 5 | $0.00009 | $0.00205 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
patch 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 yesterday.
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
/patch — 小迭代规划(规划者模式)
你现在是规划者,不是执行者。本轮你不修改任何文件、不碰版本号、不建 tag、不调 gh。
输入
$ARGUMENTS —— 本轮 patch 的主题或线索。为空时,主动扫描发现候选 patch。
流程
1. 扫描现状
- 累积计数(累积制核心): 运行
git log $(git describe --tags --abbrev=0)..HEAD --oneline得到自上次 tag 以来的 patch 提交列表与数量 —— 用户判断"何时升 minor"的依据。 - 按主题定位相关位置;若涉及内容,读对应
todo/01x-vol*.md确认这个 patch 服务于哪条 next-step(仅作上下文)。 - ⚠️ 项目 Python 脚本一律用
.venv/bin/python(有 PreToolUse hook 强制)。 - 必要时做 web search 核查事实(准确性优先,token 成本其次)。
2. 判定类型并打标(仅用于聊天讨论,不进 Issue)
| 标签 | 含义 | label 建议 |
|---|---|---|
| 内容 (feat) | 写新内容的一个片段。完成一部分内容也算 patch | feature |
| 修缮 (fix) | 错别字 / 注释错 / 代码缩进或缺行 / 事实性小错 | bug |
| 批量 (chore) | lint / frontmatter / 404 等机械修复(跨多文件也归此类) | documentation |
| 示例 (build) | 代码示例编译 / 行为修复 | bug |
| 工具链 (chore) | 脚本 / CI / 构建配置小修 | enhancement |
3. 粒度与边界(累积制 —— patch 是开发的原子单位)
- patch 是所有开发工作的原子单位,涵盖全部类型,包括写新内容的一个片段。不会因为"动了学习路径"或"写的是新内容"就升级 minor。
- 不设文件数 / 行数硬上限,也不设类型升级线。诉求太大就拆成多个 patch,不升级 minor。
- 何时升 minor,纯粹由用户手工判定,与 patch 类型无关。
4. 提案 → 讨论 → 确认(核心是讨论)
- 先用一句话讲清这轮打算做什么,作为讨论起点(类型/进度等上下文口头带过即可,别堆列表)。
- 与用户来回讨论打磨,直到用户明确确认。
- 保持灵活,不搞死板:不强制列具体文件、不强制验收标准 —— 讲明白就行。
- 未确认前,不产出 Issue。
5. 确认后,产出两样东西到聊天框(讨论的最终产物)
(a) 本轮确认的开发工作 —— 一句话总结聊定的内容。
(b) 迭代 Issue(Markdown) —— 套用 .claude/templates/iteration-issue.md(极简版:标题 + 一句话 + 一段"本轮打算做什么"),用 ```markdown 代码块包裹。用户微调后自行送 GitHub。
★ (a)(b) 都必须通俗易懂:用大白话写,少术语、别堆结构化清单,让没参与讨论的人也能一眼看懂这轮要干啥。
输出后停下。
硬约束
- ❌ 不直接执行任何文件修改。只产出讨论结果。
- ❌ 不碰版本 bump / CHANGELOG / git tag(用户自理)。
- ❌ 不调
gh issue create,不开 issue。 - ✅ 全程讨论驱动;Issue 仅在用户确认后产出。
- ✅ 输出通俗易懂:用大白话写,别堆术语 —— 用户要能看懂自己收到的 Issue。
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.
- yesterday First seen · 65 lines · 44 tokens per session scan A 974af4a6f7fe
patch is a command published in the GitHub repository Awesome-Embedded-Learning-Studio/Tutorial_AwesomeModernCPP (250 stars, last pushed 2d ago), licensed MIT. It adds 44 tokens to every session and 1,024 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 2026-08-30.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
component
Scaffold a new React component grounded in the paper-mono primitives. Requires explicit kind or a nearest-existing-component match. No empty divs, no speculative scaffolding.
memory-store
Store an insight, decision, or pattern to memory.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".