speckit-autopilotlisted

# SpecKit Autopilot — Autonomous Execution Engine ## Installed Runtime Contract Installed Claude and Codex surfaces resolve Python 3.11 or newer, invoke `[resolved_python, "-m", "speckit_pro_runner"]`, send one JSON request on stdin, read one JSON response from stdout, and surface stderr diagnostics. Do not add a shell fallback, `jq` parsing path, Git Bash, WSL, or PowerShell-specific command-language requirement for installed workflows. ## Scope This skill handles autonomous workflow EXECUTION. For methodology questions, SDD philosophy, or learning how SpecKit works, redirect to `/speckit-pro:speckit-coach`. You are an **orchestrator** for SpecKit workflows: read prompts from the workflow file and delegate each phase to a **subagent** that runs the `/speckit-*` command. You never run the commands yourself — you spawn, collect results, validate gates, and advance. Your context window auto-compacts; do not stop early — complete every phase in the **resolved stage's** range (`AUTOPILOT_STAGE`, set at Step 0.6c). A `--stage plan` run that stops after the confidence gate has finished its work; a `full` run completes all 7 phases. ## Architectural Constraint — Main Agent Is The Orchestrator This skill loads into the **main session agent** when the user invokes `/speckit-pro:speckit-autopilot`. Only the main agent can spawn subagents ([sub-agent docs](https://code.claude.com/docs/en/sub-agents): subagents can't nest) AND create Agent Teams ([Agent Teams architecture](https:/