Fire Autonomous — Development skill for Claude Code
Full autopilot — plan, execute, verify all phases autonomously after PRD is complete.
How to install Fire Autonomous
Installs to ~/.claude/skills/thierryn-fire-flow-fire-autonomous/SKILL.md
mkdir -p ~/.claude/skills/thierryn-fire-flow-fire-autonomous && curl -fsSL https://raw.githubusercontent.com/ThierryN/fire-flow/HEAD/commands/fire-autonomous.md -o ~/.claude/skills/thierryn-fire-flow-fire-autonomous/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Fire Autonomous does
description: Full autopilot — plan, execute, verify all phases autonomously after PRD is complete argument-hint: "[--from-phase N] [--to-phase N] [--max-phase-attempts 3]"
/fire-autonomous
Full autopilot after PRD is complete — plan, execute, verify, advance through all phases independently
Purpose
After discussions and PRD are complete (`/fire-1a-discuss`), this command takes over the entire build pipeline. Claude plans each phase, executes it, verifies the work (verifie
Alternatives in Development
- Implement Plan — You are tasked with implementing an approved technical plan from thoughts/shared/plans/ 10k ★
- Ralphy — My Ralph Wiggum setup, an autonomous bash script that runs Claude Code, Codex, OpenCode, Cursor agent, Qwen & 2.8k ★
- Autoresearch — Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code 2.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Gsd Autonomous
Run all remaining phases autonomously — discuss→plan→execute per phase
Grace Feature Dev
feature-dev's engine + GRACE markup + an autonomous kanban board. Interactive understand/clarify/architecture
Vdd
Execute an approved plan in phases with iterative critique loops.
Auto Trigger
After any recon/probe step, route observed signals to the right tools and fire the auto-plan (Balanced policy)
Harness Verify
Run the full verification loop before claiming any feature is complete. This is the "Ralph Wiggum Loop" - forc
Prp Execute
Execute a PRP implementation plan until fully complete
Related Agents
Aid Test Agent
Autonomously exercises the AID methodology end to end (Phases 0-5) and reports where it breaks. Use for /aid-t
Autopilot Lite
Use when you want to run iterative autonomous development with PRD and progress tracking, fresh context per it
Ticket Executor
Execute one autopilot ticket's complete per-ticket pipeline (Policy guard -> /scout -> /impl -> /ship -> artif