Autonomous Run

Autonomous Run is an Automation skill for Claude Code, published by PromptPartner in agentsmith.

185 stars5 forkson PromptPartner/agentsmithAdded 2026/09/06Repository updated 2026/09/04

agentic-aiagentic-codingai-agentsai-toolsautomationclaudeclaude-codecodexcoding-agentdeveloper-toolsgeminillmllm-agentsopen-sourceprompt-engineeringvibe-coding

Install in seconds

Install Autonomous Run

Copy Autonomous Run into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/PromptPartner/agentsmith/tree/master/skills/autonomous-run ~/.claude/skills/autonomous-run

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/PromptPartner/agentsmith.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/autonomous-run/SKILL.md in PromptPartner/agentsmith
Installs to: ~/.claude/skills/autonomous-run
Collection: One of 13 skills cataloged from this repository
Category: Automation — 2226 skills

What Autonomous Run does

Autonomous Run prepares and supervises a finite local implementation run after a terminal spec is accepted. It coordinates a maker and checker, with no pushing, merging, deployment, or external-system writes.

Autonomous Run is cataloged under Automation on DirSkills. Autonomous Run comes from a repository tagged agentic-ai, agentic-coding, ai-agents, ai-tools and automation.

Documentation

README

Excerpt

Autonomous run — bounded overnight execution

This skill is for a finite approved implementation, not a recurring watcher. For recurring work use the autonomous-loops profile. For unresolved product or architecture decisions, run Wayfinder first.

Hard gate

Do not begin implementation unless all of these are true:

The terminal spec is committed under docs/specs/ with status: accepted, accepted_by, and accepted_at. An agent may author only status: draft.
A separate implementation-ticket ID is named. The decision ticket is not executable work.
The operator explicitly invokes or authorizes start. Producing or checking a spec never self-authorizes implementation.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Autonomous Run

What else does PromptPartner publish alongside Autonomous Run?
Autonomous Run is one of 13 skills that DirSkills catalogs from PromptPartner/agentsmith, the repository it ships in. Its siblings there include Design Review, Example Skill and Handoff. Each one is a separate skill with its own page in this directory, installs the same way Autonomous Run does, and is maintained by PromptPartner in that same repository. The rest of the collection is listed on the PromptPartner/agentsmith page.
How does Autonomous Run compare to other Automation skills?
Autonomous Run ranks #1878 by stars among the 2226 Automation skills in this catalog. The most-starred ones next to it are Autonomous Loops, Autonomous Agent Harness and Automation Audit Ops. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Autonomous Run against them. Open each page to compare what they document and how they install.