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 skills add ZhangShenao/harness9 --skill autodevgit clone --depth 1 https://github.com/ZhangShenao/harness9Wrote 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/skills/zhangshenao/harness9/autodev)<a href="https://agentmods.dev/skills/zhangshenao/harness9/autodev"><img src="https://agentmods.dev/badge/skills/zhangshenao/harness9/autodev.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 5.1 | $0.00025 | $0.01094 |
| Opus 5 | $0.00013 | $0.00547 |
| Sonnet 5 | $0.00005 | $0.00219 |
| Haiku 4.5 | $0.00003 | $0.00109 |
Grade A, and why
autodev scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/autodev — Feature Auto-Development Workflow
当用户输入 /autodev <功能描述> 时,你按以下三个阶段工作。
Phase 1: 需求澄清
首先用 read_file 读取 AGENTS.md,了解项目当前模块、架构和规范(重点:第 4 节项目结构、第 5 节开发流程)。
然后向用户提 2-3 个关键澄清问题,每次只问一个:
- 功能边界:明确实现什么、不实现什么
- 验收标准:什么样的测试证明功能完成(单元测试?eval 用例?)
- 影响范围:新增文件为主还是修改已有模块
2-3 轮澄清后直接进入 Phase 2,不要过度追问。
Phase 2: Spec 生成与确认
以如下格式生成并展示 spec:
## Feature Spec: <标题>
### 功能描述
<简洁描述该功能做什么>
### 实现范围
新增文件:
- internal/<pkg>/<file>.go
- internal/<pkg>/<file>_test.go
修改文件:
- cmd/harness9/main.go(如需注册新工具)
### 验收标准
- [ ] go build ./... 通过
- [ ] go test ./... 通过
- [ ] (如涉及 Agent 行为)internal/evals/dataset/ 新增 eval 用例
### 不在范围内
- <明确列出不做的事>
展示完成后,输出以下提示,不要调用任何工具,直接结束本轮回复(TUI 会自动等待用户输入):
请确认 spec(输入「确认」继续实现),或告知需要修改的地方。
如果用户要求修改,更新 spec 后重新展示,再次等待确认。 只有用户明确输入「确认」后才进入 Phase 3。
Phase 3: 前置检查 + 委派实现
3.1 前置检查
依次用 bash 执行以下检查,任一失败则停下来告知用户并等待修复:
# 检查 Go 已安装(项目要求 1.25+)
go version
# 检查 git 可用
git --version
如果 SANDBOX_ENABLED=true,还需检查 Go 镜像是否配置:
echo "SANDBOX_IMAGE=${SANDBOX_IMAGE:-未设置}"
# 若未设置或不含 golang,提示用户在 .env 中添加:
# SANDBOX_IMAGE=golang:1.25-bookworm
3.2 创建 git worktree
从 spec 标题生成 slug(全小写,空格替换为 -,去掉非 ASCII 字母数字字符),然后执行:
示例:"Add WebSocket 支持" → "add-websocket-"(中文字符去掉)→ 可简化为 "add-websocket-support"
git worktree add .autodev/<slug> -b feature/autodev-<slug>
用 bash 获取绝对路径:
readlink -f .autodev/<slug>
3.3 委派 dev sub-agent
调用 task 工具委派 dev sub-agent:
task("dev", "以下是需要实现的 Feature Spec:\n\n<spec 全文>\n\n工作目录(git worktree 绝对路径):<worktreePath>")
3.4 处理结果
成功(sub-agent 返回 AUTODEV_RESULT: SUCCESS):
从 sub-agent 返回结果中提取 BRANCH: <branch-name>,然后执行合并:
# 将 feature 分支合并到当前分支
git merge feature/autodev-<slug>
若合并成功:
- 展示:「✓ 已合并到当前分支:feature/autodev-」
- 清理 worktree:
git worktree remove .autodev/<slug>
若合并产生冲突:
- 展示冲突文件列表
- 保留 worktree:「存在合并冲突,worktree 保留在 .autodev/,请手动解决冲突」
- 告知用户解决后执行:
git worktree remove .autodev/<slug> --force
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.
- 7d ago First seen · 132 lines · 25 tokens per session scan A 99b1a15a190b
autodev is a skill published in the GitHub repository ZhangShenao/harness9 (138 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 1,094 once invoked, about $0.0001 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…