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 instructions/yinzhenyu-su/weekly-git-summary/claude-mdgit clone --depth 1 https://github.com/yinzhenyu-su/weekly-git-summaryWrote 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/instructions/yinzhenyu-su/weekly-git-summary/claude-md)<a href="https://agentmods.dev/instructions/yinzhenyu-su/weekly-git-summary/claude-md"><img src="https://agentmods.dev/badge/instructions/yinzhenyu-su/weekly-git-summary/claude-md.svg" alt="Measured on agentmods" 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 | $0.02716 | $0.02716 |
| Opus 5 | $0.01358 | $0.01358 |
| Sonnet 5 | $0.00543 | $0.00543 |
| Haiku 4.5 | $0.00272 | $0.00272 |
Grade A, and why
weekly-git-summary CLAUDE.md 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 5d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
该文件为 Claude Code (claude.ai/code) 在此代码库中工作时提供指导。
项目概述
这是 weekly-git-summary,一个跨平台的 CLI 工具,用于生成 Git 提交记录的周报汇总。它自动扫描 Git 仓库,提取指定日期范围内的提交历史,并以多种格式输出结果(文本、JSON、Markdown、HTML)。
主要特性
- 多维度过滤: 支持多作者过滤、消息模式匹配(正则表达式)
- 传统提交规范: 支持 Conventional Commits 解析和统计分析
- 时间范围预设: 支持预设时间范围(today, this-week, last-month 等)
- 统计分析: 提供提交统计、参与者分析、类型分布等
- 国际化文档: 完整的中英文文档支持
关键命令
构建和开发
# 构建 CLI 工具
bun run build.ts
# 构建脚本从 scripts/cli.ts 创建 build/cli.js
# 使用 Bun 的构建 API,ESM 格式,目标为 Node.js
测试 CLI
# 构建后,本地测试 CLI
node build/cli.js --help
# 使用参数测试
node build/cli.js -d ~/projects -s 2023-01-01 -u 2023-01-31
node build/cli.js --json
node build/cli.js --md
node build/cli.js --html
# 新功能测试 - 时间范围预设
node build/cli.js --time-range today
node build/cli.js --time-range this-week
node build/cli.js --time-range last-month
# 传统提交规范分析
node build/cli.js --conventional --time-range this-week
# 消息模式过滤(支持正则表达式)
node build/cli.js --message-pattern "feat|fix" --conventional
node build/cli.js --message-pattern "用户|登录|认证"
# 目录路径 - 支持包含空格的路径(多种转义方式)
node build/cli.js -d "Program Files/MyProject" # 引号包裹
node build/cli.js --dir "My\ Documents/Projects" # 引号内反斜杠转义
node build/cli.js --dir "/Library/Application\ Support" # 多个反斜杠转义
# 作者过滤 - 支持多个作者和空格名称(多种转义方式)
node build/cli.js -a "John Doe" # 单个作者(引号包裹)
node build/cli.js --author "Zhang San" # 单个作者(引号包裹)
node build/cli.js --author 'Li Ming Wang' # 单个作者(单引号包裹)
node build/cli.js -a "John\ Doe" # 单个作者(引号内反斜杠转义)
node build/cli.js -a "Alice" -a "Bob" # 多个作者过滤(OR 关系)
node build/cli.js -a "John Doe" --author "Jane Smith" # 混合使用短参数和长参数
node build/cli.js -a "Dr\ John\ Doe" -a "Mary\ Jane\ Watson" # 多个作者反斜杠转义
架构设计
跨平台策略
项目使用 TypeScript CLI 包装器(scripts/cli.ts):
- 使用
os.platform()检测操作系统 - 自动委托给平台特定的脚本:
- Windows:
weekly-git-summary.js(Node.js) - 不再依赖 PowerShell - macOS/Linux:
weekly-git-summary.sh(Bash) 或回退到weekly-git-summary.js(Node.js)
- Windows:
- 透明地将所有命令行参数传递给底层脚本
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.
- 5d ago First seen · 259 lines · 2,716 tokens per session scan A e286365a0c29
weekly-git-summary CLAUDE.md is an instructions file published in the GitHub repository yinzhenyu-su/weekly-git-summary (203 stars, last pushed 8d ago), licensed MIT. It adds 2,716 tokens to every session, about $0.0136 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 instructions, from other repositories
deva CLAUDE.md
Claude Code instructions for thevibeworks/deva, covering claude.md, deva architecture: container-based agent sandboxing and we're following issue-based development (ibd) workflow.
claude-auto-resume CLAUDE.md
Instructions for terryso/claude-auto-resume, covering claude.md, project overview, installation, method 1: using makefile (recommended) and install globally.
deva AGENTS.md
AGENTS.md instructions for thevibeworks/deva: Repo guidance for coding agents lives in CLAUDE.md (architecture, issue-based development workflow) and workflows/ (issue, commit, PR, release conventions). Read those before changing anything.
process-mcp AGENTS.md
AGENTS.md instructions for Kruceo/process-mcp, covering agents.md — process mcp server, key decisions, commit conventions (pipoca-style), examples and versioning.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.