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 skills/miles990/claude-software-skills/auto-dev-setupnpx skills add miles990/claude-software-skills --skill auto-dev-setupgit clone --depth 1 https://github.com/miles990/claude-software-skillsWrote 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/miles990/claude-software-skills/auto-dev-setup)<a href="https://agentmods.dev/skills/miles990/claude-software-skills/auto-dev-setup"><img src="https://agentmods.dev/badge/skills/miles990/claude-software-skills/auto-dev-setup.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 | $0.00023 | $0.01025 |
| Opus 5 | $0.00012 | $0.00513 |
| Sonnet 5 | $0.00005 | $0.00205 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
auto-dev-setup 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 6d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-Dev Setup Skill
為任何專案設定 Human-in-the-Loop 自動開發流程。
使用時機
當用戶說:
- "幫我設定 auto-dev"
- "我想在這個專案用自動開發"
- "設定 GitHub Actions 自動開發流程"
設定流程
Step 1: 確認需求
使用 AskUserQuestion 確認:
1. Workflow 來源
□ 使用 Reusable Workflow(推薦,自動更新)
□ 複製完整 Workflow(可自訂)
2. Skills 來源
□ 使用 claude-software-skills
□ 使用自己的 skills repo
□ 不使用額外 skills
3. 額外設定
□ 需要任務佇列(定時處理)
□ 需要 Feedback 處理(PR 上繼續迭代)
Step 2: 建立目錄結構
mkdir -p .github/workflows
mkdir -p .claude/memory/{learnings,failures,decisions,patterns,strategies}
mkdir -p .github/ISSUE_TEMPLATE
Step 3: 建立 Workflow(二擇一)
方式 A: Reusable Workflow(推薦)
# .github/workflows/auto-dev.yml
name: 🤖 Auto-Dev
on:
issues:
types: [labeled]
issue_comment:
types: [created]
workflow_dispatch:
inputs:
goal:
description: '開發目標'
required: true
jobs:
auto-dev:
uses: {SKILLS_REPO}/.github/workflows/auto-dev-reusable.yml@main
with:
goal: ${{ github.event.inputs.goal || '' }}
secrets:
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
替換 {SKILLS_REPO} 為實際的 repo 路徑。
方式 B: 完整 Workflow
從 claude-software-skills 複製:
.github/workflows/auto-dev.yml.github/workflows/auto-dev-feedback.yml.github/workflows/auto-dev-queue.yml
Step 4: 建立 Issue Template
# .github/ISSUE_TEMPLATE/auto-dev.yml
name: 🤖 Auto-Dev Task
description: 建立一個自動開發任務
labels: ["auto-dev"]
body:
- type: textarea
id: goal
attributes:
label: 目標
description: 描述開發目標
validations:
required: true
Step 5: 初始化 Memory
# .claude/memory/index.md
# 專案記憶索引
## 最近學習
<!-- LEARNINGS_START -->
<!-- LEARNINGS_END -->
## 失敗經驗
<!-- FAILURES_START -->
<!-- FAILURES_END -->
Step 6: 提醒設定 Secret
告知用戶:
請到 Repository Settings → Secrets → Actions
新增 ANTHROPIC_API_KEY
使用方式速查
| 操作 | 方式 |
|---|---|
| 觸發自動開發 | Issue + auto-dev label |
| 命令觸發 | 留言 /evolve [目標] |
| 繼續迭代 | PR 上留言 /evolve [調整] |
| 手動觸發 | Actions → Run workflow |
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.
- 6d ago First seen · 155 lines · 23 tokens per session scan A 848e63d2bb1a
auto-dev-setup is a skill published in the GitHub repository miles990/claude-software-skills (20 stars, last pushed 7mo ago), licensed MIT. It adds 23 tokens to every session and 1,025 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
github-actions-ci
Structure GitHub Actions workflows — jobs, steps, caching, matrix builds, secrets, and a quality gate that blocks merges.
ci-cd-patterns
CI/CD pipeline patterns, workflow configuration, and release automation best practices.
devops-automation
DevOps自动化技能 - CI/CD流水线生成、Docker管理、部署脚本.
wizard
Generate an interactive bash wizard that walks a human through a manual procedure — third-party setup, a one-off migration, an A→B state transition — opening URLs, capturing values, confirming each step, and writing .env files and GitHub Actions secrets.
github-hardening
Use when updating or reviewing GitHub-side hardening guidance for derived repositories, including required settings, rulesets, scanning, review protections, and workflow permissions. Use terraform-hardening instead for Terraform-backed changes under config/infra. Do not use for ordinary in-repo implementation changes…
repo-adaptation
Use when adapting or customizing this repository to meet the needs of the source code under src/, including language and framework needs, dependencies, runtime behavior, Docker, Makefile targets, and customization surfaces. Do not use for routine bug fixes, small refactors, pure workflow validation…