Agent skill

Claude Code Clawdbot

by win4r in win4r/claude-code-clawdbot-skill

Run Claude Code (Anthropic) from this host via the claude CLI (Agent SDK) in headless mode (-p) for codebase analysis, refactors, test fixing, and structured output.

No licenceAuto-check: warningsAI & LLM Engineering

Install Claude Code Clawdbot

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add win4r/claude-code-clawdbot-skill --skill claude-code-clawdbot -a claude-code

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

GitHub CLI
$ gh skill install win4r/claude-code-clawdbot-skill claude-code-clawdbot --agent claude-code

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

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
claude-code-clawdbot
GitHub stars
123
Token cost
~2.5k tokens
SKILL.md length
1,023 words
Files
4 (incl. scripts)
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

Run Claude Code (Anthropic) from this host via the claude CLI (Agent SDK) in headless mode (-p) for codebase analysis, refactors, test fixing, and structured output.

  • Works in 12 steps: Run a headless prompt in a repo → Allow tools (auto-approve) → Get structured output → …
  • The user asks to use Claude Code
  • SKILL.md covers Quick checks, Core workflow, Notes (important) and High‑leverage Claude Code tips…, plus 4 more sections
  • Runs Python scripts from its folder; calls git, claude and npm

What it does

Claude Code Clawdbot is an agent skill from win4r/claude-code-clawdbot-skill. Run Claude Code (Anthropic) from this host via the claude CLI (Agent SDK) in headless mode (-p) for codebase analysis, refactors, test fixing, and structured output. Use when the user asks to use Claude Code, run claude -p, use Plan Mode, auto-approve tools with --allowedTools, generate JSON output, or integrate Claude Code into Clawdbot workflows/cron.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `README.md` and `scripts/claude_code_run.py`).

It sits in AI & LLM Engineering, covering Structured output and tool calling, Planning and Building AI agents. It works with tmux. The repository describes itself as: A Clawdbot skill to run Claude Code (Anthropic) on the host via the claude CLI (Agent SDK).

When your agent uses it

  • The user asks to use Claude Code
  • Auto-approve tools with --allowedTools
  • Generate JSON output
  • Integrate Claude Code into Clawdbot workflows/cron

Example prompts

  • “/claude-code-clawdbot”

Requirements

  • Python 3
  • Node.js

Workflow steps

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

  1. Run a headless prompt in a repo
  2. Allow tools (auto-approve)
  3. Get structured output
  4. Add extra system instructions
  5. Always give Claude a way to verify (tests/build/screenshots)
  6. Explore → Plan → Implement (use Plan Mode)
  7. Manage context aggressively: /clear and /compact
  8. Rewind aggressively: /rewind (checkpoints)
  9. Prefer CLAUDE.md for durable rules; keep it short
  10. Permissions: deny > ask > allow (and scope matters)
  11. Bash env vars don’t persist; use CLAUDE_ENV_FILE for persistence
  12. Hooks beat “please remember” instructions

What it can do on your machine

Read from SKILL.md and the folder at commit 759f398. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • git
    • claude
    • npm

    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

Claude Code Clawdbot loads about 2.5k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 1,023 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

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: warnings

The automated check found patterns that need a careful read before installing.

  • NoteMentions a .env fileSKILL.md:125
    Use deny rules to block secrets (e.g. `.env`, `secrets/**`).
  • WarningMentions a paste, webhook or tunnelling service often used to send data outSKILL.md:240
    ver: { host: true, allowedHosts: ['xxxx.ngrok-free.app'] }

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); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,023 words (~2,506 tokens).

“Use the locally installed Claude Code CLI reliably.”

— opening of SKILL.md by win4r
name
claude-code-clawdbot

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files (scripts) in the repository root of win4r/claude-code-clawdbot-skill.

  • SKILL.md
  • .gitignore
  • README.md
  • scripts/claude_code_run.py

Open the folder on GitHubat commit 759f398

Compare with similar skills

Claude Code Clawdbot 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.

Claude Code Clawdbot compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claude Code Clawdbot this skillwin4r/claude-code-clawdbot-skill123—~2.5kAutomated safety check: WarnNone
Building AI Agent On Cloudflaremajiayu000/claude-skill-registry6661 repos~2.3kAutomated safety check: PassMIT
Pydantic AI Harnesspydantic/pydantic-ai20k—~4.9kAutomated safety check: PassMIT
Google Agents CLI Adk Codepifferologo/cloud-agents-cli1291 repos~768Automated safety check: PassApache-2.0
Coding Agentswarmclawai/swarmclaw688—~900Automated safety check: PassMIT
CodexMicrock/ordinary-claude-skills4032 repos~2.8kAutomated safety check: PassCustom licence

Similar skills

  • Building AI Agent On Cloudflare

    majiayu000/claude-skill-registry

    Builds AI agents on Cloudflare using the Agents SDK with state management, real-time WebSockets, scheduled tasks, tool integration, and chat capabilities.

    666 GitHub starsUsed in 1 repo~2.3k tokens
    Backend & APIsAuto-check passed
  • Pydantic AI Harness

    pydantic/pydantic-ai

    Official

    Adds optional capabilities to Pydantic AI agents from pydantic-ai-harness, led by Code Mode, which runs many tool calls as one sandboxed Python script.

    20k GitHub stars~4.9k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Google Agents CLI Adk Code

    pifferologo/cloud-agents-cli

    This skill should be used when the user wants to "write agent code", "build an agent with ADK", "add a tool", "create a callback", "define an agent", "use state management", or needs ADK (Agent…

    129 GitHub starsUsed in 1 repo~768 tokens
    AI & LLM EngineeringAuto-check passed
  • Coding Agent

    swarmclawai/swarmclaw

    Delegate coding tasks to external coding agents (Claude Code, Codex, Pi, OpenCode) via shell.

    688 GitHub stars~900 tokensUpdated 3 mo ago
    Agent WorkflowsAuto-check passed
  • Codex

    Microck/ordinary-claude-skills

    Execute Codex CLI for code analysis, refactoring, and automated code changes.

    403 GitHub starsUsed in 2 repos~2.8k tokens
    AI & LLM EngineeringAuto-check passed
  • Build Agents

    vercel/vercel-plugin

    Official

    Default guidance for building AI agents. An agent skill from vercel/vercel-plugin.

    301 GitHub stars~1.4k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

Works with

Questions about Claude Code Clawdbot

What does Claude Code Clawdbot do?

Run Claude Code (Anthropic) from this host via the claude CLI (Agent SDK) in headless mode (-p) for codebase analysis, refactors, test fixing, and structured output. Claude Code Clawdbot is an agent skill from win4r/claude-code-clawdbot-skill. Run Claude Code (Anthropic) from this host via the claude CLI (Agent SDK) in headless mode (-p) for codebase analysis, refactors, test fixing, and structured output.

When should I use Claude Code Clawdbot?

Claude Code Clawdbot fits situations like: the user asks to use Claude Code; auto-approve tools with --allowedTools; generate JSON output; integrate Claude Code into Clawdbot workflows/cron.

How do I install Claude Code Clawdbot in Claude Code?

Run `npx skills add win4r/claude-code-clawdbot-skill --skill claude-code-clawdbot -a claude-code`. Or copy the skill folder (the win4r/claude-code-clawdbot-skill repository) into .claude/skills/claude-code-clawdbot in your project. Claude Code loads it when a task matches its description.

How do I install Claude Code Clawdbot in Codex?

Run `npx skills add win4r/claude-code-clawdbot-skill --skill claude-code-clawdbot -a codex`. Or copy the skill folder (the win4r/claude-code-clawdbot-skill repository) into .agents/skills/claude-code-clawdbot in your project. Codex loads it when a task matches its description.

Can I use Claude Code Clawdbot 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 win4r/claude-code-clawdbot-skill --skill claude-code-clawdbot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claude-code-clawdbot, .gemini/skills/claude-code-clawdbot, .github/skills/claude-code-clawdbot and .opencode/skills/claude-code-clawdbot in your project.

What does Claude Code Clawdbot need to run?

Going by SKILL.md and its folder, Claude Code Clawdbot needs Python for the scripts in its folder and the command-line tools its instructions call (git, claude and npm). Our summary lists: Python 3; Node.js.

Does Claude Code Clawdbot 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 Claude Code Clawdbot safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): mentions a paste, webhook or tunnelling service often used to send data out. Read the flagged lines before installing; the check is not a guarantee either way. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Claude Code Clawdbot use?

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

How many tokens does Claude Code Clawdbot use?

About 2.5k tokens (SKILL.md is roughly 10k 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 Claude Code Clawdbot?

Skills that share tags, products or a category with Claude Code Clawdbot: Building AI Agent On Cloudflare (majiayu000/claude-skill-registry, 666 stars), Pydantic AI Harness (pydantic/pydantic-ai, 20k stars), Google Agents CLI Adk Code (pifferologo/cloud-agents-cli, 129 stars) and Coding Agent (swarmclawai/swarmclaw, 688 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claude Code Clawdbot?

win4r (a GitHub user) maintains it in win4r/claude-code-clawdbot-skill, which has 123 GitHub stars. The repository was last updated on February 1, 2026.

Source: win4r/claude-code-clawdbot-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.