ai-agent-team: Skill for Claude Code

.claude/skills/changelog-generator/SKILL.md

changelog-generator is a skill for Claude Code from peterfei/ai-agent-team. It costs 48 tokens per session (3,023 once invoked), scanned A, original, MIT.

A tool that reads Git commit history and creates or updates a CHANGELOG.md file, a human-readable record of software changes. It understands Conventional Commits, a common commit-message format.

In plain words
What is it for?
Generate full or version-specific changelogs, update an unreleased section, configure output, and prepare release entries.
Why use it?
It removes the repetitive work of sorting commits, formatting release notes, and updating the change history by hand.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; positional $N argument.

This is peterfei/ai-agent-team's own configuration. It tells Claude Code how to work on ai-agent-team itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-agent-team configures →

Reuse

Borrowing it

Nothing to install: this file belongs to peterfei/ai-agent-team. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/peterfei/ai-agent-team/main/.claude/skills/changelog-generator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/peterfei/ai-agent-team

Made for: Claude Code.

Wrote 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.

agentmods badge for changelog-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/peterfei/ai-agent-team/changelog-generator/github.svg)](https://agentmods.dev/skills/peterfei/ai-agent-team/changelog-generator)
Your own site
<a href="https://agentmods.dev/skills/peterfei/ai-agent-team/changelog-generator"><img src="https://agentmods.dev/badge/skills/peterfei/ai-agent-team/changelog-generator/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.

agentmods 80×15 button for changelog-generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/peterfei/ai-agent-team/changelog-generator"><img src="https://agentmods.dev/badge/skills/peterfei/ai-agent-team/changelog-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,023 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium MCP Rug Pull · line 386
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00048 $0.03023
Opus 5 $0.00024 $0.01511
Sonnet 5 $0.00010 $0.00605
Haiku 4.5 $0.00005 $0.00302

Measured 10d ago against content hash d7d2c8db63db, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

changelog-generator 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 10d ago.

The scan reads SKILL.md. This mod also ships 16 executable files (bin/cli.js, jest.config.js, src/core/ChangelogGenerator.js, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/changelog-generator/SKILL.md · 556 lines

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.

changelog-generator - 智能变更日志生成器

概述

当用户需要生成或更新 CHANGELOG 时,此 skill 会自动完成以下流程:

  1. 分析 Git 提交历史
  2. 根据 Conventional Commits 规范解析提交
  3. 智能分类和组织变更
  4. 生成符合 Keep a Changelog 标准的 CHANGELOG.md
  5. 支持版本发布和增量更新

支持的触发指令

用户可以通过以下方式触发此 skill:

  • "changelog" - 简易触发词
  • "变更日志" - 简易触发词
  • "帮我生成 CHANGELOG" - 生成完整的 CHANGELOG
  • "更新 CHANGELOG" - 增量更新 CHANGELOG
  • "发布新版本" - 发布正式版本
  • "初始化 changelog 配置" - 创建配置文件

工作流程

步骤 1: 初始化配置(首次使用)

命令:

cd ~/.claude/skills/changelog-generator
npm install

# 在项目目录中初始化配置
cd /path/to/your/project
changelog-generate init

配置文件: .changelogrc.json

交互式配置会询问:

  • 当前版本号
  • 语言选择(中文/英文)
  • 是否使用 emoji
  • 是否显示作者信息

步骤 2: 生成 CHANGELOG

场景 A: 首次生成完整 CHANGELOG

# 生成所有历史提交的 CHANGELOG
changelog-generate generate --all

# 生成指定范围的 CHANGELOG
changelog-generate generate --from v1.0.0 --to v2.0.0

场景 B: 增量更新 CHANGELOG

# 更新 [Unreleased] 区域
changelog-generate update

# 从指定标签开始更新
changelog-generate update --from v2.0.0

场景 C: 发布新版本

# 自动确定版本号(交互式)
changelog-generate release

# 手动指定版本号
changelog-generate release --version 2.1.0

# 指定日期
changelog-generate release --version 2.1.0 --date 2023-11-10

步骤 3: 输出文件

默认输出路径: ./CHANGELOG.md

生成的 CHANGELOG 示例:

# Changelog

All notable changes to this project will be documented in this file.

## [Unreleased]

## [2.0.0] - 2023-11-10

### 💥 BREAKING CHANGES

- **api:** Remove deprecated v1 endpoints (#123)

### ✨ Features

- **auth:** Add JWT authentication (#120)
- **api:** Add user profile endpoint (#121)

### 🐛 Bug Fixes

- **ui:** Fix button alignment issue (#122)

### 📝 Documentation

- Update API documentation

## [1.0.0] - 2023-10-01

...

核心功能

1. 智能提交解析

支持 Conventional Commits 规范:

feat(auth): add login functionality
^    ^      ^
type scope  subject

BREAKING CHANGE: Remove old auth API

支持的提交类型:

  • feat: ✨ Features
  • fix: 🐛 Bug Fixes
  • docs: 📝 Documentation
  • style: 💄 Styles (可隐藏)
  • refactor: ♻️ Code Refactoring
  • perf: ⚡ Performance
  • test: ✅ Tests
  • build: 📦 Build System
  • ci: 👷 CI/CD
  • chore: 🔧 Chores (可隐藏)

Read the full file on GitHub · 556 lines

Changes

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.

  1. 10d ago First seen · 556 lines · 48 tokens per session scan A d7d2c8db63db

Subscribe to this mod's changes

changelog-generator is a skill published in the GitHub repository peterfei/ai-agent-team (434 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 3,023 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.