Stun — Development skill for Claude Code
Drive the current phase from Planned to Complete in this session, pausing only for your decisions (run in accept-edits or auto mode for unattended apply).
How to install Stun
Installs to ~/.claude/skills/davekruse-phaser-stun/SKILL.md
mkdir -p ~/.claude/skills/davekruse-phaser-stun && curl -fsSL https://raw.githubusercontent.com/davekruse/phaser/HEAD/commands/stun.md -o ~/.claude/skills/davekruse-phaser-stun/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Stun does
description: "Drive the current phase from Planned to Complete in this session, pausing only for your decisions (run in accept-edits or auto mode for unattended apply)" argument-hint: "[optional: scope] [optional: openspec change id]" model: opus disable-model-invocation: true
phaser:stun — Drive the phase to Complete
You dispatch ONE step. The step you dispatch chains to the next one itself, and so on, until the phase is Complete or something stops the run. You do not loop, wait, or
Alternatives in Development
- Om Dump — Freeform capture mode 4.6k ★
- Discipline — Toggle discipline mode — auto-invoke verification, brainstorming-before-coding, and review checks 2.8k ★
- Claude Code Guide — The Complete Claude Code CLI Guide - Live & Auto-Updated Every 2 Days 2.6k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Claude Sprint Agent
A wrapper script that runs an unattended Claude Code "sprint" in headless mode, monitors the output for a DONE
Manage Managed Silo Lifecycle
Apply start / pause / delete lifecycle transitions to a managed E2B or Daytona cloud silo with farm silo , for
Pause Work
Create context handoff when pausing work mid-phase
Jidoka Build
Run the build phase — dispatch implementation agents per the planned graph
Drive Issue
Use when told to drive, run, or own ONE named cqlite issue to done/merged in this session (e.g. "drive issue 3
Kg Conflicts
List and help resolve elements shaped by two competing head decisions (concurrent edits) in the kgai knowledge
Related Agents
Direction Challenger
(/auto) Pre-direction challenger. Reads the local board before research planner, attacks the inertia and assum
ChatGPT Spec Review
Coordinates ChatGPT spec review in a dedicated session (manual ChatGPT-web, automated OpenAI API, or parallel
Project Structure Reviewer
Read-only audit of the current repo against spec/project/project-structure/, producing a severity-sorted findi