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/mcpp-community/mcpp/mcpp-contributingnpx skills add mcpp-community/mcpp --skill mcpp-contributinggit clone --depth 1 https://github.com/mcpp-community/mcppWhat 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 | $0.00053 | $0.03728 |
| Opus 5 | $0.00026 | $0.01864 |
| Sonnet 5 | $0.00011 | $0.00746 |
| Haiku 4.5 | $0.00005 | $0.00373 |
Grade A, and why
mcpp-contributing 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.
How it starts
The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcpp 项目开发贡献规范
Overview
mcpp 项目的贡献流程:先创建 Issue → 切分支 → 实现改动 → 提交 PR → CI 通过 → Review 合入。
- 仓库:https://github.com/mcpp-community/mcpp
- 构建:
mcpp build(C++23 模块自举) - 测试:
mcpp test覆盖tests/**/*.cpp,tests/e2e/提供真实二进制的端到端脚本 - CI:GitHub Actions,base 为
main的 PR 触发分平台构建、测试与 E2E 检查
核心原则
禁止直接 push main
所有改动必须通过 PR 合入 main,无论改动大小。这包括:
- 代码改动(feat / fix / refactor)
- 文档改动(docs / skills / .agents/)
- 配置改动(mcpp.toml / .xlings.json / CI workflow)
- 版本号 bump(必须通过 PR,不能直接 push)
唯一例外:紧急 hotfix 需要 --admin 合入,但也必须先创建 PR。
违规示例(不允许):
# ✗ 直接 push 到 main
git commit -m "docs: add skill" && git push origin main
# ✗ 绕过分支保护
git push origin feature:main
正确做法:
# ✓ 始终走 PR 流程
git checkout -b docs/add-release-skill
git commit -m "docs: add release skill"
git push -u origin docs/add-release-skill
gh pr create --title "docs: add release skill" --body "..."
# 等 CI 通过后合入
贡献流程
1. 创建 Issue(必须)
所有贡献先创建 Issue,特别是新功能。避免重复工作,留下讨论记录。
Bug 修复
gh issue create \
--title "fix: 简短描述" \
--body "## 复现步骤
1. ...
## 期望行为
...
## 实际行为
...
## 环境
- mcpp 版本:\`mcpp --version\`
- OS:"
新功能
gh issue create \
--title "feat: 简短描述" \
--body "## 动机
...
## 设计思路
...
## 涉及模块
..."
代码优化
gh issue create \
--title "refactor: 简短描述" \
--body "## 当前问题
...
## 优化方案
..."
2. 创建分支
必须从最新 main 创建分支,禁止在 main 上直接开发。
git checkout main && git pull origin main
git checkout -b <type>/<short-description>
# type: feat / fix / refactor / test / docs / chore
分支命名规范:
feat/xxx— 新功能fix/xxx— Bug 修复refactor/xxx— 重构test/xxx— 测试docs/xxx— 文档chore/xxx— 版本 bump、配置、依赖更新
3. 实现改动
开发要求
- 遵循现有代码风格(查看相邻代码)
- 模块导入用
import std;和import mcpp.xxx; - 只改需要改的,不顺手重构不相关代码
- 平台相关代码放在
src/platform/目录下
构建验证
# 用现有 bootstrap mcpp 自举构建
mcpp build
# 选择刚生成的 target/**/bin/mcpp(Windows 为 mcpp.exe),不要硬编码宿主 triple
<fresh-mcpp-binary> --version
测试
# C++ 单元/集成测试:由刚构建的二进制发现 tests/**/*.cpp
<fresh-mcpp-binary> test
# 端到端测试:显式把刚构建的二进制交给脚本
# 路径必须是刚构建产物的绝对路径;Windows 使用 mcpp.exe。
MCPP=<absolute-path-to-fresh-mcpp-or-mcpp.exe> bash tests/e2e/01_help_and_version.sh
MCPP=<absolute-path-to-fresh-mcpp-or-mcpp.exe> bash tests/e2e/<relevant-test>.sh
# 新功能按变更契约补充 focused unit/integration 和/或 E2E 覆盖
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 · 339 lines · 53 tokens per session scan A e21f0674af16
mcpp-contributing is a skill published in the GitHub repository mcpp-community/mcpp (114 stars, last pushed 2d ago), licensed Apache-2.0. It adds 53 tokens to every session and 3,728 once invoked, about $0.0003 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 skills, from other repositories
readable-cpp
Readable C/C++/Rust/CUDA code rules inspired by The Art of Readable Code. Use when writing, reviewing, or refactoring C, C++, Rust, or CUDA code. Enforces short functions, flat control flow, clear naming, readable structure, and idiomatic patterns.
cpp
Comprehensive C/C++ programming reference covering everything from C11-C23 and C++11-C++23, system programming, CUDA GPU computing, debugging tools, Rust interop, and advanced topics. Use for: C/C++ questions, C/C++ interview preparation, modern language features, RAII/memory management, templates/generics, CUDA…
mcpp-style-ref
为 mcpp 项目应用 Modern/Module C++ (C++23) 编码风格。适用于编写或审查带模块的 C++ 代码、命名标识符、组织 .cppm/.cpp 文件,或用户提及 mcpp、module C++、现代 C++ 风格时。.
mbun-runtime-debugging
调试 mbun 运行时测试失败/崩溃时用。提供仓库实测可用的定位配方——选二进制、单文件跑测、gdb 抓 backtrace、按 API 定位源码、常见坑排查清单、何时跳过。凡处理 bun 测试跑不过/段错误/hang/断言失败,先读本 skill 再动手,避免每个 task 重复摸索拖慢。.
dev-process
在本仓开发任何改动前用。规定 issue 先行的开发流程,按 bugfix / 优化 / 新功能分流;新功能须经 issue 充分讨论并在 .agents/docs 落地设计方案;衔接 tdd-workflow 与本体验证 / 测试 / CI / PR 规范。开发前先读本 skill。.
issue-reporting
向本仓提交 issue / 发起讨论时用。规定一份好问题反馈的 SOP——软件/版本、报错信息、初步分析、相关资料,并去除本地隐私(用户名/token 等替换)。凡要创建 issue、反馈 bug、发起讨论,先读本 skill 再动手。.