Borrowing it
Nothing to install: this file belongs to mcpp-community/mcpp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mcpp-community/mcpp/main/.agents/skills/mcpp-docs-style/SKILL.mdgit clone --depth 1 https://github.com/mcpp-community/mcppWrote 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/mcpp-community/mcpp/mcpp-docs-style)<a href="https://agentmods.dev/skills/mcpp-community/mcpp/mcpp-docs-style"><img src="https://agentmods.dev/badge/skills/mcpp-community/mcpp/mcpp-docs-style/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/mcpp-community/mcpp/mcpp-docs-style"><img src="https://agentmods.dev/badge/skills/mcpp-community/mcpp/mcpp-docs-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00118 | $0.09371 |
| Opus 5.5 | $0.00047 | $0.03748 |
| Sonnet 5.5 | $0.00024 | $0.01874 |
| Haiku 4.5 | $0.00012 | $0.00937 |
Grade A, and why
mcpp-docs-style 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 — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcpp 文档规范
本规范回答六个问题:这份文档的归属(第一节)、为什么要有这一章(第二节)、 怎么写(第三至七节)、它必须对得上什么(第八节)、 它欠多少覆盖(第十节)、怎么评审它(第十四节)。
最核心的一条在第一节:用户文档是已实现功能的使用手册,不是设计说明。
代码注释与 commit message 不受本规范约束 —— 它们的读者、篇幅与目的都不同, 那里允许并鼓励叙述「为什么」以及实测过程。
一、文档的归属:三棵树与各自的准入判据
一份文档属于哪棵树,由读者决定,不由篇幅或主题决定。
| 树 | 读者 | 准入判据(问自己这一句) | 稳定性 |
|---|---|---|---|
docs/** |
手上有任务的人 | 手上有这个任务的人,没有它做不完 | 增量;旧拼法留作别名 |
docs/specs/** |
对着机制做实现的人:索引作者、下游工具、贡献者 | 没有它,两个独立实现会不一致 | 编号 + 版本 + 状态机 |
.agents/docs/** |
做这次改动的人,以及以后问「为什么是这样」的人 | 做了一个决定,理由否则会丢 | 落地即不可变 |
.agents/skills/** |
照着做的人或 agent | 这是步骤,不是解释 | 随流程变 |
用户文档是已实现功能的使用手册
这是本规范最核心的一条。
docs/**服务的是要把事情做成的用户。它写 mcpp 已经实现的东西怎么用, 不写这些东西为什么被设计成这样,也不写什么设计了、什么还没设计。
不写进用户文档的四类内容,它们全部属于 .agents/docs/:
- 设计理由与取舍 ——「为什么是一个机制而不是两个」「这个边界由模型的性质 决定而不是本文档的雄心」。
- 被否掉的替代 ——「三种替代方案都不能去掉它」「某原语写出来又撤回了」。
- 路线图与设计状态 ——「计划中」「将来会支持」「已设计未实现」「下一步是」。 用户文档里一个能力只有两种状态:能用(带版本下界)与不支持(一句话)。
- 实现内幕 —— 除非用户不知道它就会用错。
判据(逐段问一遍):把这一段删掉,读者还能不能正确地用?
- 能 → 删掉,或移进设计记录。
- 不能 → 它不是设计论证,是使用信息;改写成事实陈述,去掉论证语气。
边界写成事实,不写成论证。 「当前边界」一节(第十节要求它必须存在)是一份 清单,不是一段说理:
| 不采用 | 采用 |
|---|---|
| OpenMP offload 与 stdpar 没有可分的岛,因此落在这套机制的论域之外 —— 这是模型的性质,而不是本文档雄心的缺口。 | 未支持:OpenMP offload、stdpar、Metal、HIP 的 AMD 平台。 |
之所以不发出 accel 字段,是因为该字段的含义是「实测所得」,而 mcpp 目前无从测量,把声明写进一个语义为实测的字段会让身份说谎。 |
mcpp pack 不产出 accel 字段;需要它的发布方在描述符里手写。 |
理由就是不给。要理由的读者是另一类读者,他去读设计记录 —— 而用户文档 不链接设计记录(见上面的引用方向)。
已测状态(2026-09-08):九个用户章节含设计论证短语,05 21 处、13 8 处、
20 6 处,20 另有两个设计型标题。清理按
.agents/docs/2026-09-08-documentation-architecture-three-trees.md 的分阶段进行。
另外三条最容易被违反的推论
- 用户章节不记历史。 「过去是 X,2026.8.16 起改成 Y」是设计记录的句子。
章节陈述今天是什么;版本相关写下界(
2026.9.6.5+)。 - 设计记录落地后不再编辑,除了追加状态行或一个具名带日期的更正块。 就地改写会让一份「某时刻的记录」悄悄变成「对现在的断言」。
- 用户章节里出现「必须 / 禁止」,说明内容属于规范。 把它移进
docs/specs/,章节引用它。只有规范有规范性语气。
引用方向是规则,不是习惯
docs/ ──▶ docs/specs/ 允许:引用精确语义
docs/ ─╳─ .agents/docs/ 禁止
docs/specs/ ──▶ .agents/docs/ 允许,仅限元数据表里的溯源行
docs/specs/ ──▶ docs/ 允许
.agents/docs/ ──▶ 任何 允许
代码注释 ──▶ docs/ 或 specs/ 允许,且被引用的文件必须存在
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 Changed · +401 lines · +42 tokens per session 158fe1669922
- 2mo ago First seen · 155 lines · 76 tokens per session scan A 6daefa774316
mcpp-docs-style is a skill published in the GitHub repository mcpp-community/mcpp (196 stars, last pushed yesterday), licensed Apache-2.0. It adds 118 tokens to every session and 9,371 once invoked, about $0.0005 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 2026-08-30.
mcpp-docs-style compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcpp-docs-stylemcpp-community/mcpp | Skill | 196 | yesterday | Apache-2.0 | A | 118 | Claude Code, Codex |
| readable-cppcrazyguitar/cppcheatsheet | Skill | 293 | 9d ago | MIT | A | 63 | Claude Code |
| cppcrazyguitar/cppcheatsheet | Skill | 293 | 9d ago | MIT | A | 0 | Claude Code |
| zoom-meeting-sdk-unrealanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 41 | Claude Code |
| doca-argpNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 277 | Claude Code, Codex |
| cpu-kernelshuggingface/kernels | Skill | 783 | yesterday | Apache-2.0 | A | 89 | Claude Code |
| review-trtmc-prNVIDIA/TensorRT-Model-Connect | Skill | 289 | today | Apache-2.0 | A | 105 | Codex |