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/qinye6/pi-ccg/commitgit clone --depth 1 https://github.com/qinye6/pi-ccgWhat 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 | $0.00017 | $0.01327 |
| Opus 5 | $0.00009 | $0.00664 |
| Sonnet 5 | $0.00003 | $0.00265 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
commit 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 2d 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 commit — 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit - 智能 Git 提交
分析当前改动，生成 Conventional Commits 风格的提交信息。
使用方法
/commit [options]
选项
| 选项 | 说明 |
|---|---|
--no-verify |
跳过 Git 钩子 |
--all |
暂存所有改动 |
--amend |
修补上次提交 |
--signoff |
附加签名 |
--emoji |
包含 emoji 前缀 |
--scope <scope> |
指定作用域 |
--type <type> |
指定提交类型 |
执行工作流
🔍 阶段 1：仓库校验
[模式：检查]
- 验证 Git 仓库状态
- 检测 rebase/merge 冲突
- 读取当前分支/HEAD 状态
📋 阶段 2：改动检测
[模式：分析]
- 获取已暂存与未暂存改动
- 若暂存区为空：
--all→ 执行git add -A- 否则提示选择
✂️ 阶段 3：拆分建议
[模式：建议]
按以下维度聚类：
- 关注点（源代码 vs 文档/测试）
- 文件模式（不同目录/包）
- 改动类型（新增 vs 删除）
若检测到多组独立变更（>300 行 / 跨多个顶级目录），建议拆分。
✍️ 阶段 4：生成提交信息
[模式：生成]
格式：[emoji] <type>(<scope>): <subject>
- 首行 ≤ 72 字符
- 祈使语气
- 消息体：动机、实现要点、影响范围
语言：根据最近 50 次提交判断中文/英文
📦 阶段 5：Context 自动归档（若 .context/ 存在）
[模式：上下文归档]
前置判断：
- 若
.context/目录不存在 → 在提交成功后输出提示：💡 建议执行 /ccg:context init 启用决策追踪，不阻断 - 若
.context/存在 → 执行以下步骤
从 git diff 自动生成 ContextEntry：
- 获取当前分支名：
git branch --show-current - 获取暂存区变更：
git diff --cached --stat+git diff --cached（完整 diff） - 分析 diff 生成 ContextEntry：
summary：从阶段 4 生成的 commit message 中取首行decisions：分析 diff 中的关键变更（新增依赖、架构调整、接口变更、配置修改），推断决策理由bugs：若 commit type 为fix，从 diff 中提取 bug 症状、根因、修复方式changes.files：从git diff --cached --name-only提取tests：若变更包含测试文件，记录测试相关信息
- 合并 session.log（可选）：若
.context/current/branches/<branch>/session.log存在且非空，将其中的手动记录合并到 decisions/bugs 中，然后清空 session.log - 脱敏：扫描 token/key/password/secret 模式 → 替换为
[REDACTED] - 追加：将 ContextEntry 作为一行追加到
.context/history/commits.jsonl - 重生成：更新
.context/history/commits.md人类视图 - 暂存：
git add .context/history/ - Trailer：在 commit message 中添加
Context-Id: <uuid>trailer
ContextEntry 格式参见 /ccg:context 命令中的 Schema 定义。
失败降级：若归档过程出错，不阻断提交。写入 minimal ContextEntry（仅 summary + files），继续正常提交。
✅ 阶段 6：执行提交
[模式：执行]
git commit [-S] [--no-verify] [-s] -F .git/COMMIT_EDITMSG
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.
- 2d ago First seen · 152 lines · 17 tokens per session scan A 59548e39c6d2
commit is a command published in the GitHub repository qinye6/pi-ccg (10 stars, last pushed 8d ago), licensed MIT. It adds 17 tokens to every session and 1,327 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to commit, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.