Runner Down — Development skill for Claude Code
Stop an agent-runner slot.
How to install Runner Down
Installs to ~/.claude/commands/on-keyday-agent-harness-runner-down.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/on-keyday/agent-harness/HEAD/.claude/commands/runner-down.md -o ~/.claude/commands/on-keyday-agent-harness-runner-down.md Restart Claude Code, or start a new session, for it to be picked up.
What Runner Down does
description: Stop an agent-runner slot. Auto-detects whether it was launched via runner-autostart.py register and routes to `unregister` if so. Refuses if tasks are assigned or if it would self-terminate. argument-hint: "" allowed-tools: Bash
Gracefully stop an agent-runner slot. **Refuses if the runner has any task currently assigned, or if downing it would terminate this very session.**
Use the canonical scripts — do not invoke `kill` directly. `scripts/runner.sh down` handles S
Alternatives in Development
- 14 Dev Runner — Prompt 14: Create Development Runner 2.2k ★
- Ctf 24h Fleet — 24h unattended multi-target Web CTF fleet loop runner 1.1k ★
- Omk — Evidence-gated runner for Codex, Claude Code, OpenCode, and local coding agents 141 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Runner Up
Spawn an agent-runner slot via scripts/runner.sh up (auto-resolves server-cid from env). persist keyword route
Obsidian Vault Kit
A knowledge vault Claude Code maintains for you — document and session-history ingest into a linked Obsidian g
Setup Copilot
Universal Claude Copilot setup. Auto-detects context and routes to the appropriate setup command.
Unity Ralph
Relentless verify-fix loop — refuses to stop until the project is clean. Runs unity-verifier repeatedly with c
Cmon
Corrective for a verbose reply - distill what was just said down to its core essentials and restate it in as f
Build Prompt
Build a high-quality Claude prompt through a guided interview. Pass a starting input as the argument: /build-p
Related Agents
Grays Run
Mechanical test runner (Haiku tier). Auto-detects pytest, jest, vitest, playwright. Runs tests, reports pass/f
Fe Test Runner
Dedicated test execution. Returns only a categorized summary, keeping failure stack traces out of the parent c
Decision Agent
You are a Tier 2 decision agent for Correctless Auto Mode. You receive a structured decision request and retur