Agent skill

Autodev

by jh941213 in jh941213/my-cc-harness

Ralph Loop based autonomous development loop. An agent skill from jh941213/my-cc-harness.

No licenceAuto-check: notesAgent Workflows

Install Autodev

skills CLI
$ npx skills add jh941213/my-cc-harness --skill autodev -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jh941213/my-cc-harness autodev --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jh941213/my-cc-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills_en/autodev .claude/skills/autodev && rm -rf skills-src

Use ~/.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/

Facts

Skill name
autodev
GitHub stars
126
Token cost
~1.5k tokens
SKILL.md length
293 words
Files
1
Skills in repo
62
Repo updated
First seen
Licence
None found

At a glance

Ralph Loop based autonomous development loop. An agent skill from jh941213/my-cc-harness.

  • Works in 4 steps: Configuration Collection → Loop Initialization → Iteration Execution (every session) → …
  • Tasks that involve Autonomous loops
  • SKILL.md covers Core Principle, Phase 0: Configuration…, Phase 1: Loop Initialization and Phase 2: Iteration Execution…, plus 5 more sections
  • Calls git, python3 and npm

What it does

Autodev is an agent skill from jh941213/my-cc-harness. Ralph Loop based autonomous development loop. A Stop Hook intercepts session termination and completes PRD items one by one with automatic commits. Triggers: "autodev", "autonomous development", "run overnight", "ralph loop", "auto development" Anti-triggers: "implement it yourself", "do it once", "manual"

Its SKILL.md is about 1.5k 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 Agent Workflows, covering Autonomous loops and PRD writing.

When your agent uses it

  • Tasks that involve Autonomous loops
  • Tasks that involve PRD writing

Example prompts

  • “autodev”
  • “autonomous development”
  • “run overnight”
  • “/autodev”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Grep, Glob, Agent

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Configuration Collection
  2. Loop Initialization
  3. Iteration Execution (every session)
  4. Completion Report

What it can do on your machine

Read from SKILL.md and the folder at commit e9210e2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit
    • Bash
    • Grep
    • Glob
    • Agent

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • python3
    • npm
    • vitest
    • make

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git and npm, which can reach the network depending on how they are called.

    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

Autodev loads about 1.5k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 293 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Edit, Bash, Grep, Glob, Agent

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 293 words (~1,530 tokens).

“Stop Hook based autonomous development loop. Completes PRD/checklist items one by one with automatic commits. Leave it running overnight and a PR is waiting when you arrive at work.”

— opening of SKILL.md by jh941213
name
autodev
allowed-tools
Read, Write, Edit, Bash, Grep, Glob, Agent
user-invocable
true
disable-model-invocation
false

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills_en/autodev of jh941213/my-cc-harness.

Open the folder on GitHubat commit e9210e2

Compare with similar skills

Autodev 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.

Autodev compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Autodev this skilljh941213/my-cc-harness126—~1.5kAutomated safety check: NotesNone
Handoffanombyte93/prd-taskmaster604—~5kAutomated safety check: PassMIT
Ralphjulianromli/opencode-template1441 repos~1.1kAutomated safety check: PassNone
Ralph Loop InitTechDufus/oh-my-claude174—~4.6kAutomated safety check: NotesMIT
Ralphjellydn/my-ai-tools1233 repos~1.8kAutomated safety check: PassMIT
Foreman Grill DocsVisionForge-OU/foreman443—~1.6kAutomated safety check: PassCustom licence

Similar skills

  • Handoff

    anombyte93/prd-taskmaster

    Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff.

    604 GitHub stars~5k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Ralph

    julianromli/opencode-template

    Autonomous agent loop for completing features. An agent skill from julianromli/opencode-template.

    144 GitHub starsUsed in 1 repo~1.1k tokens
    Product & Project ManagementAuto-check passed
  • Ralph Loop Init

    TechDufus/oh-my-claude

    Transform approved plans into ralph loop infrastructure. An agent skill from TechDufus/oh-my-claude.

    174 GitHub stars~4.6k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check: notes
  • Ralph

    jellydn/my-ai-tools

    Convert PRDs to prd.json format for the Ralph autonomous agent system

    123 GitHub starsUsed in 3 repos~1.8k tokens
    Product & Project ManagementAuto-check passed
  • Foreman Grill Docs

    VisionForge-OU/foreman

    Headless grilling pass that challenges an approved implementation plan against the existing codebase and domain model, then writes an ADR draft and a PRD draft into the Foreman feature directory.

    443 GitHub stars~1.6k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed
  • Implementation Plan Generator

    withkynam/vibecode-pro-max-kit

    Writes a project's one implementation plan at the right depth level, saved into a dated task folder alongside any spec file and reports.

    1.1k GitHub stars~1.4k tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed

More from jh941213/my-cc-harness

All 62 skills in this repo
  • API Design Principles

    jh941213/my-cc-harness

    REST 및 GraphQL API 설계 원칙 가이드. An agent skill from jh941213/my-cc-harness.

    126 GitHub starsUsed in 20 repos~3.4k tokens
    Auto-check passed
  • Tailwind Design System

    jh941213/my-cc-harness

    Build scalable design systems with Tailwind CSS, design tokens, component libraries, and responsive patterns.

    126 GitHub starsUsed in 10 repos~4.7k tokens
    Auto-check passed
  • Docs Architecture

    jh941213/my-cc-harness

    Generate/update architecture docs — ARCHITECTURE.md (codemap), architecture diagrams (C4 mermaid), ADRs (MADR), data model ERD.

    126 GitHub stars~923 tokensUpdated 2 mo ago
    Auto-check: notes
  • Auto Memory

    jh941213/my-cc-harness

    A skill your agent uses when starting substantial work in a repo (implementation, fixes, deploys, debugging), when first exploring a new repo, or when finishing work that produced reusable knowledge.

    126 GitHub stars~890 tokensUpdated 2 mo ago
    Auto-check passed
  • Async Python Patterns

    jh941213/my-cc-harness

    Python asyncio 및 async/await 패턴 가이드. An agent skill from jh941213/my-cc-harness.

    126 GitHub starsUsed in 14 repos~4.7k tokens
    Auto-check passed
  • Python Testing Patterns

    jh941213/my-cc-harness

    Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development.

    126 GitHub starsUsed in 17 repos~5.4k tokens
    Auto-check passed

Questions about Autodev

What does Autodev do?

Ralph Loop based autonomous development loop. An agent skill from jh941213/my-cc-harness. Autodev is an agent skill from jh941213/my-cc-harness. Ralph Loop based autonomous development loop.

When should I use Autodev?

Autodev fits situations like: tasks that involve Autonomous loops; tasks that involve PRD writing.

How do I install Autodev in Claude Code?

Run `npx skills add jh941213/my-cc-harness --skill autodev -a claude-code`. Or copy the skill folder (skills_en/autodev in jh941213/my-cc-harness) into .claude/skills/autodev in your project. Claude Code loads it when a task matches its description.

How do I install Autodev in Codex?

Run `npx skills add jh941213/my-cc-harness --skill autodev -a codex`. Or copy the skill folder (skills_en/autodev in jh941213/my-cc-harness) into .agents/skills/autodev in your project. Codex loads it when a task matches its description.

Can I use Autodev 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 jh941213/my-cc-harness --skill autodev -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/autodev, .gemini/skills/autodev, .github/skills/autodev and .opencode/skills/autodev in your project.

What does Autodev need to run?

Going by SKILL.md and its folder, Autodev needs the command-line tools its instructions call (git, python3, npm, vitest and make). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Grep, Glob, Agent.

Does Autodev access the network?

SKILL.md contains no URLs. Its commands use git and npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Autodev safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Autodev use?

No licence was found for Autodev or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Autodev use?

About 1.5k tokens (SKILL.md is roughly 6.1k 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 Autodev?

Skills that share tags, products or a category with Autodev: Handoff (anombyte93/prd-taskmaster, 604 stars), Ralph (julianromli/opencode-template, 144 stars), Ralph Loop Init (TechDufus/oh-my-claude, 174 stars) and Ralph (jellydn/my-ai-tools, 123 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Autodev?

jh941213 (a GitHub user) maintains it in jh941213/my-cc-harness, which has 126 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on August 3, 2026.

Source: jh941213/my-cc-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.