autospec-run

Community

Autonomously implement and merge queued specs

Authorberlinguyinca
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Autospec-run turns a pre-built GitHub issue implementation queue into shipped, reviewable, explainable code changes without requiring the operator to micromanage every PR.

Core Features & Use Cases

  • Autonomous monitor (Phase 4): Claims ready auto-implement issues, runs the implement→test→PR→self-review→admin-squash-merge loop, then immediately continues as new merges unblock the queue.
  • Quality and safety gates (Phases 4–6): Enforces dependency closure, path conflict avoidance, doc drift checks, rebase-and-retest before merge, and ends with a consolidated completion report.
  • Distributed queue coordination: Supports multi-machine workers via GitHub labels plus a run-state comment/heartbeat mechanism to coordinate claims safely.
  • Model-fit filtering: Optionally filters candidate issues by ctx:* and reasoning:* ceilings using ~/.autospec/model-profiles.yml and reports deferred items at run end.

Quick Start

Run autospec-run on your repo’s populated queue with the command: /autospec-run --profile claude-sonnet-cloud

Dependency Matrix

Required Modules

ghjqgitcurlollama

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: autospec-run
Download link: https://github.com/berlinguyinca/autospec/archive/main.zip#autospec-run

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.