run-autonomous

run-autonomous is a skill for Claude Code from Jerry0022/dotclaude. It costs 90 tokens per session (8,732 once invoked), scanned B, original, MIT.

An autonomous task-running workflow for when you are away from the computer. It lets agents carry out implementation, desktop interaction, and live browser or app testing without ongoing supervision, with an optional computer shutdown afterward.

In plain words
What is it for?
Use it for tasks you want agents to run independently while you are away, including optional automatic resume and shutdown settings.
Why use it?
It removes the need to supervise a long-running task continuously while preserving a confirmation step before autonomous work begins.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the devops plugin — 25 skills, 12 agents, 5 hooks, 3 MCP servers shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Jerry0022/dotclaude
Claude Code
/plugin install devops

Made for: Claude Code.

Or install devops, the plugin that ships this one along with the rest of its 25 skills, 12 agents, 5 hooks, 3 MCP servers.

Wrote 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.

agentmods badge for run-autonomous

README.md
[![agentmods](https://agentmods.dev/badge/skills/jerry0022/dotclaude/run-autonomous.svg)](https://agentmods.dev/skills/jerry0022/dotclaude/run-autonomous)
Your own site
<a href="https://agentmods.dev/skills/jerry0022/dotclaude/run-autonomous"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/run-autonomous.svg" alt="Measured on agentmods" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,732 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00090 $0.08732
Opus 5 $0.00045 $0.04366
Sonnet 5 $0.00018 $0.01746
Haiku 4.5 $0.00009 $0.00873

Measured 5d ago against content hash a30200c39446, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade B, and why

run-autonomous scanned grade B with 1 finding 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 5d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

but are NOT covered by the current `~/.claude/settings.json` allow-list. Closes
plugins/devops/skills/run-autonomous/SKILL.md · 653 lines

How it starts

The opening of the file, as written. The whole thing — 653 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Autonomous

User is leaving the PC. Collect the task, prime permissions, confirm, then work independently.

Step 0 — Load Extensions

Silently check (do not surface "not found"):

  1. ~/.claude/skills/run-autonomous/SKILL.md + reference.md
  2. {project}/.claude/skills/run-autonomous/SKILL.md + reference.md
  3. Merge: project > global > plugin defaults

Step 0.1 — Auto-Start Prompt Detection

If the incoming user message starts with AUTONOMOUS_AUTOSTART:, this is the 3-minute timeout from Step 4 firing. The user is likely AFK.

  1. Pending-question guard: If an AskUserQuestion is currently active (the Step 4b confirmation, a clarifying question, or anything else), do NOT auto-start. Re-arm a fresh one-shot cron at now + 3min with the same AUTONOMOUS_AUTOSTART: prompt and context, log "Autostart verschoben — offene Frage aktiv", continue waiting.
  2. If no question is pending: parse task, mode, desktop, shutdown, autoResume, branch from the prompt.
  3. Output once: "3-Minuten-Timeout — starte jetzt autonom."
  4. Skip Steps 1-4 entirely. Permissions were already primed in the parent session.
  5. If autoResume=yes, arm the resume cron now (Step 4e) — Step 4c never ran on this path.
  6. Jump directly to Step 5 with the parsed context. The Post-Confirmation Lockout is active from this moment.

Step 0.2 — Auto-Resume Handler

If the incoming user message starts with AUTONOMOUS_RESUME:, the Step 4e one-shot cron has fired: the 5h token window has reset and any Claude worktrees that were hard-capped mid-run should be nudged to continue. The user is AFK — do this without questions, then stop. Steps 1-8 do NOT apply.

  1. git worktree list --porcelain → collect every worktree whose branch starts with claude/ (each is an active Claude session; same detection as setup-cleanup).
  2. Classify each. A worktree is done if its root holds AUTONOMOUS-DONE.flag, or an AUTONOMOUS-REPORT.html with COMPLETED status and no AUTONOMOUS-RESUME.json. Skip done worktrees — never re-trigger finished work.
  3. For each remaining (mid-task / hard-capped) worktree, resume it with a single weiter: use mcp__ccd_session_mgmt__list_sessions to find the live session bound to that worktree path, then mcp__ccd_session_mgmt__send_message with the one word weiter. If the session-mgmt tools are unavailable, list the worktree paths that need a manual weiter instead of nudging.
  4. Output a short summary: nudged / skipped-done / manual-needed. Do not start new work — only continue what was interrupted.

Read the full file on GitHub · 653 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 5d ago First seen · 653 lines · 90 tokens per session scan B a30200c39446

Subscribe to this mod's changes

run-autonomous is a skill published in the GitHub repository Jerry0022/dotclaude (5 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 8,732 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens