Agent Builder
shareAI-lab/learn-claude-code
Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.
A skill your agent uses when asked about harness9 architecture, module design, or how components interact — explains the system design
Install Architecture Overview
$ npx skills add ZhangShenao/harness9 --skill architecture-overview -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ZhangShenao/harness9 architecture-overview --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ZhangShenao/harness9.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/architecture-overview .claude/skills/architecture-overview && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "architecture-overview" agent skill from https://github.com/ZhangShenao/harness9/tree/master/skills/architecture-overview into .claude/skills/architecture-overview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-overview", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ZhangShenao/harness9/tree/master/skills/architecture-overviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ZhangShenao/harness9 --skill architecture-overview -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ZhangShenao/harness9 architecture-overview --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZhangShenao/harness9.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/architecture-overview .agents/skills/architecture-overview && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "architecture-overview" agent skill from https://github.com/ZhangShenao/harness9/tree/master/skills/architecture-overview into .agents/skills/architecture-overview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-overview", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ZhangShenao/harness9 --skill architecture-overview -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ZhangShenao/harness9 architecture-overview --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZhangShenao/harness9.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/architecture-overview .cursor/skills/architecture-overview && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "architecture-overview" agent skill from https://github.com/ZhangShenao/harness9/tree/master/skills/architecture-overview into .cursor/skills/architecture-overview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-overview", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ZhangShenao/harness9.git --path skills/architecture-overview--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ZhangShenao/harness9 --skill architecture-overview -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ZhangShenao/harness9 architecture-overview --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZhangShenao/harness9.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/architecture-overview .gemini/skills/architecture-overview && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "architecture-overview" agent skill from https://github.com/ZhangShenao/harness9/tree/master/skills/architecture-overview into .gemini/skills/architecture-overview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-overview", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ZhangShenao/harness9 architecture-overviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ZhangShenao/harness9 --skill architecture-overview -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ZhangShenao/harness9.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/architecture-overview .github/skills/architecture-overview && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "architecture-overview" agent skill from https://github.com/ZhangShenao/harness9/tree/master/skills/architecture-overview into .github/skills/architecture-overview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-overview", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ZhangShenao/harness9 --skill architecture-overview -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ZhangShenao/harness9 architecture-overview --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ZhangShenao/harness9.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/architecture-overview .opencode/skills/architecture-overview && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "architecture-overview" agent skill from https://github.com/ZhangShenao/harness9/tree/master/skills/architecture-overview into .opencode/skills/architecture-overview/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architecture-overview", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
architecture-overview- GitHub stars
- 141
- Token cost
- ~717 tokens
- SKILL.md length
- 119 words
- Files
- 1
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when asked about harness9 architecture, module design, or how components interact — explains the system design
- Works in 3 steps: 自然终止：len(responseMsg.ToolCalls) == 0 → MaxTurns：默认 50，可通过 WithMaxTurns 配置 → Context 取消：外部 cancel() 或超时
- Asked about harness9 architecture
- SKILL.md covers 核心设计原则, 标准 ReAct 循环, 模块依赖关系 and 关键数据流, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Architecture Overview is an agent skill from ZhangShenao/harness9. Use when asked about harness9 architecture, module design, or how components interact — explains the system design
Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering. The repository describes itself as: Local-First · 轻量级 · 功能完备 · 生产可用的通用 Agent 框架. The licence is MIT.
When your agent uses it
- Asked about harness9 architecture
- How components interact — explains the system design
Example prompts
- “/architecture-overview”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 自然终止：len(responseMsg.ToolCalls) == 0
- MaxTurns：默认 50，可通过 WithMaxTurns 配置
- Context 取消：外部 cancel() 或超时
What it can do on your machine
Read from SKILL.md and the folder at commit 6d2ae52. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are go).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Architecture Overview loads about 717 tokens when it runs. Until then it costs about 34 tokens; SKILL.md has 119 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from ZhangShenao/harness9 at commit 6d2ae52, republished under its MIT licence (© ZhangShenao). 119 words, ~717 tokens.
Download SKILL.mdSave it as
.claude/skills/architecture-overview/SKILL.md (or your agent's skills folder).- name
- architecture-overview
- description
- Use when asked about harness9 architecture, module design, or how components interact — explains the system design
- trigger
- architecture, design, how does, module, component, structure
harness9 架构概览
核心设计原则
| 原则 | 说明 |
|---|---|
| 简洁 | 最小化抽象层，极少的直接依赖 |
| 完备 | 覆盖 Agent 运行所需的全部核心模块 |
| 生产可用 | 错误恢复、超时控制、路径沙箱、并发安全 |
标准 ReAct 循环
Turn N:
LLM(messages + tools) → 推理 + 工具调用决策
→ 并发执行所有工具调用 → Observation 注入 context
→ Turn N+1
自然终止：模型不再发起工具调用 → 输出最终回复三重终止保障：
- 自然终止：
len(responseMsg.ToolCalls) == 0 - MaxTurns：默认 50，可通过
WithMaxTurns配置 - Context 取消：外部
cancel()或超时
模块依赖关系
cmd/harness9 (入口)
├── internal/context (System Prompt 组装)
│ └── internal/skills (Skills 解析 + 索引)
├── internal/engine (ReAct 主循环)
│ ├── internal/provider (LLM 调用)
│ ├── internal/tools (工具注册 + 执行)
│ └── internal/schema (数据类型)
└── internal/env (配置加载)关键设计决策：接口定义在使用者侧
tools.Registry接口定义在tools包，engine包依赖它engine.PromptBuilder接口定义在engine包，context包实现它skills.UseSkillTool通过 Go 结构类型满足tools.BaseTool接口，不需要 importtools包（避免循环依赖）
关键数据流
TUI 模式
用户输入 → RunTUI → eng.RunStream(ctx, prompt)
→ engine.Event stream → 逐 token 追加到对话视图
→ ToolCalls → Spinner 动画 + 耗时计数
→ EventDone → 最终回复渲染到屏幕CLI 模式（管道 / CI）
用户输入 → RunCLI → eng.Run(ctx, prompt)
→ runLoop → LLM Generate
→ ToolCalls → 并发执行 → ToolResults → 继续循环
→ 最终回复打印到 stdoutSystem Prompt 组装
DefaultPromptBuilder.Build() 按顺序组装：
- 基础 Prompt：角色定义 + workDir
- AGENTS.md：项目级规范（文件不存在时跳过）
- Skills 索引：
- name: description列表（为空时跳过）
完整内容示例：
You are harness9, an expert coding assistant...
## Project Guidelines (AGENTS.md)
{AGENTS.md 全文}
## Available Skills
Use the `use_skill` tool to load full content of any skill when needed.
- go-coding-standards: Use when writing or reviewing Go code...
- debugging-guide: Use when debugging Go errors...Provider 抽象
type LLMProvider interface {
Generate(ctx, messages, tools) (Message, error)
GenerateStream(ctx, messages, tools) (<-chan StreamChunk, error)
}当前实现：
OpenAIProvider：兼容所有 OpenAI Chat Completions API（包括 OpenRouter、Azure）AnthropicProvider：Anthropic Messages API
Anthropic 约束：user/assistant 消息必须严格交替，禁止连续 assistant 消息。
工具系统
type BaseTool interface {
Name() string
Definition() schema.ToolDefinition // JSON Schema，传给 LLM
Execute(ctx context.Context, args json.RawMessage) (string, error)
}内置工具：
| 工具 | 说明 |
|---|---|
bash | Shell 命令执行，workDir 为 CWD |
read_file | 文件读取，4096 字节截断 |
write_file | 文件写入，自动 mkdir |
edit_file | 字符串替换编辑，多级模糊匹配 |
use_skill | 按需加载 Skill 全文 |
所有文件工具通过 safePath() 校验路径，防止 Path Traversal 攻击。
© ZhangShenao, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/architecture-overview of ZhangShenao/harness9.
Open the folder on GitHubat commit 6d2ae52
Compare with similar skills
Architecture Overview next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Architecture Overview this skillZhangShenao/harness9 | 141 | — | ~717 | Automated safety check: Pass | MIT | |
| Agent BuildershareAI-lab/learn-claude-code | 78k | 4 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Add Uint Supportpytorch/pytorch | 104k | 2 repos | ~2.3k | Automated safety check: Pass | Custom licence | |
| LLM Benchmarking with lm-evaluation-harnessOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3k | Automated safety check: Pass | MIT | |
| Segment Anything Model GuideOrchestra-Research/AI-Research-SKILLs | 13k | 8 repos | ~3.3k | Automated safety check: Pass | MIT | |
| 1passwordtrpc-group/trpc-agent-go | 1.9k | 14 repos | ~656 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Add Uint Support
pytorch/pytorch
Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.
LLM Benchmarking with lm-evaluation-harness
Orchestra-Research/AI-Research-SKILLs
Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.
Segment Anything Model Guide
Orchestra-Research/AI-Research-SKILLs
Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.
1password
trpc-group/trpc-agent-go
Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.
Planning With Files
jarrodwatts/claude-code-config
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage.
More from ZhangShenao/harness9
Debugging Guide
ZhangShenao/harness9
A skill your agent uses when debugging Go errors, test failures, or unexpected behavior — step-by-step diagnosis approach
Go Coding Standards
ZhangShenao/harness9
A skill your agent uses when writing or reviewing Go code — explains harness9 project coding conventions and patterns
Commit
ZhangShenao/harness9
A skill your agent uses when the user invokes /commit or asks to commit changes, after a code review has been completed and the changes are confirmed ready to stage and commit to git.
Cr
ZhangShenao/harness9
A skill your agent uses when the user invokes /cr, requests a code review, or before committing to verify correctness, security, and quality of new or modified code in the working tree.
PR
ZhangShenao/harness9
A skill your agent uses when the user invokes /pr or asks to push changes and open a pull request, after commits are ready to be pushed to a remote branch and merged into the main branch.
Autodev
ZhangShenao/harness9
Feature auto-development — clarify requirements, generate spec, dispatch dev sub-agent to implement and merge into current branch
Related
Categories
Questions about Architecture Overview
What does Architecture Overview do?
A skill your agent uses when asked about harness9 architecture, module design, or how components interact — explains the system design. Architecture Overview is an agent skill from ZhangShenao/harness9.
When should I use Architecture Overview?
Architecture Overview fits situations like: asked about harness9 architecture; how components interact — explains the system design.
How do I install Architecture Overview in Claude Code?
Run `npx skills add ZhangShenao/harness9 --skill architecture-overview -a claude-code`. Or copy the skill folder (skills/architecture-overview in ZhangShenao/harness9) into .claude/skills/architecture-overview in your project. Claude Code loads it when a task matches its description.
How do I install Architecture Overview in Codex?
Run `npx skills add ZhangShenao/harness9 --skill architecture-overview -a codex`. Or copy the skill folder (skills/architecture-overview in ZhangShenao/harness9) into .agents/skills/architecture-overview in your project. Codex loads it when a task matches its description.
Can I use Architecture Overview in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ZhangShenao/harness9 --skill architecture-overview -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/architecture-overview, .gemini/skills/architecture-overview, .github/skills/architecture-overview and .opencode/skills/architecture-overview in your project.
What does Architecture Overview need to run?
SKILL.md names no scripts, command-line tools or credentials: Architecture Overview is instructions for the agent only.
Does Architecture Overview access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Architecture Overview safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Architecture Overview use?
Architecture Overview is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Architecture Overview use?
About 717 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Architecture Overview?
Skills that share tags, products or a category with Architecture Overview: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Add Uint Support (pytorch/pytorch, 104k stars), LLM Benchmarking with lm-evaluation-harness (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Segment Anything Model Guide (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Architecture Overview?
ZhangShenao (a GitHub user) maintains it in ZhangShenao/harness9, which has 141 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 10, 2026.
Source: ZhangShenao/harness9 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.