Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

模块化 AI 编程技能系统,将混乱的智能体输出转化为结构化、可追溯、生产就绪的代码 「智能路由 + 工作流 + 知识库 + 命令驱动」 不仅仅是编程!

License

Notifications You must be signed in to change notification settings

nightwhite/helloagents

Repository files navigation

HelloAGENTS v2 (helloagents_v2 skill)

This repo ships one unified dev/maintenance skill: helloagents_v2/. It supports auto routing + end-to-end workflow + per-project command permissions via helloagents/config.toml.

中文:README_CN.md


Install / Deploy (manual copy)

1) Get the repo

git clone https://github.com/nightwhite/helloagents.git
cd helloagents

2) Copy the skill into your AI CLI config directory

Copy helloagents_v2/ to:

Source Target
helloagents_v2/ <CLI_CONFIG_ROOT>/skills/helloagents_v2/

Common <CLI_CONFIG_ROOT>:

  • Claude Code: ~/.claude/
  • Codex CLI: ~/.codex/

macOS/Linux (Claude Code):

cp -R helloagents_v2 ~/.claude/skills/helloagents_v2

macOS/Linux (Codex CLI):

cp -R helloagents_v2 ~/.codex/skills/helloagents_v2

Windows PowerShell (Claude Code example):

Copy-Item -Recurse helloagents_v2 $env:USERPROFILE\.claude\skills\helloagents_v2

3) Restart & verify

Restart your AI CLI, then enter/trigger the helloagents_v2 skill first (how you do this depends on your CLI: pick the skill, or explicitly invoke the skill name in chat).

After explicitly invoking the helloagents_v2 skill, run:

~help

Per-project permissions (recommended)

Each project can allow/deny commands via:

  • Path: <PROJECT_ROOT>/helloagents/config.toml
  • PROJECT_ROOT defaults to your CLI working directory (cwd)

If this file is missing, the skill will auto-initialize it before running any command (default: allow all commands).

Manual initialization (optional):

mkdir -p helloagents
cp <CLI_CONFIG_ROOT>/skills/helloagents_v2/assets/templates/config.toml helloagents/config.toml

Modes:

  • denylist: allow everything by default, disable risky commands in deny = ["~rollback", ...]
  • allowlist: only allow commands listed in allow = ["~plan", "~review"]

Common commands (minimal)

  • ~help: show allowed commands for this project + descriptions
  • ~plan <request>: run until design and generate a package (stops before develop)
  • ~exec: pick and run a package under helloagents/plan/ (handles unarchived/incomplete)
  • ~auto <request>: run end-to-end (subject to rules & permissions)
  • ~review / ~test / ~validate: review / test / validate
  • ~rollback: rollback (recommended to disable per project)

Upgrade / Uninstall

Upgrade:

  • Replace <CLI_CONFIG_ROOT>/skills/helloagents_v2/ with the new version
  • Your project helloagents/config.toml stays intact

Uninstall:

  • Delete <CLI_CONFIG_ROOT>/skills/helloagents_v2/

About

模块化 AI 编程技能系统,将混乱的智能体输出转化为结构化、可追溯、生产就绪的代码 「智能路由 + 工作流 + 知识库 + 命令驱动」 不仅仅是编程!

Resources

License

Contributing

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 100.0%

AltStyle によって変換されたページ (->オリジナル) /