Kill — Development skill for Claude Code
Interrupt a worker if running, then mark it dead.
How to install Kill
Installs to ~/.claude/skills/expardus-fleet-kill/SKILL.md
mkdir -p ~/.claude/skills/expardus-fleet-kill && curl -fsSL https://raw.githubusercontent.com/exPardus/fleet/HEAD/commands/kill.md -o ~/.claude/skills/expardus-fleet-kill/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Kill does
description: 'Interrupt a worker if running, then mark it dead. Terminal — only respawn brings it back.' argument-hint: ''
Kill fleet worker `$1`.
**This is terminal.** A `dead` worker is sticky: no log line and no recompute resurrects it, and the only exit is `fleet respawn $1`.
Before running anything, confirm with the operator that they mean this worker and not `fleet interrupt $1` (which kills only the current turn and leaves the worker alive). Once confirmed, run `fl
Alternatives in Development
- Epic Review — Mark epic review requested, approved, or changes requested 243.5k ★
- /triage — Quick triage to decide: submit or kill 1.8k ★
- Herdr Reviewr — Review your coding agent's diff in a terminal pane and send line comments back to Claude Code, Codex, OpenCode 823 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Respawn
Fresh session for a worker — same name, cwd, mode; journal and drained mailbox carried over. The context-reset
Fleet Resume
Bring a fleet run back after the machine died - reopen the workers whose context survived, respawn the ones wh
Agent Toast
No more babysitting the terminal - Agent Toast pings you the instant Claude Code or Codex CLI needs you, then
Idea Evaluator
Open-source startup idea validator for Claude Code. Tells you if your idea is DEAD, ALIVE or INSUFFICIENT_DATA
Dsh Baton
Pass the baton from Claude Code or Codex to a local DeepSeek Harness. An MCP server that hands off tasks and b
Tessera
Keep your coding agents in view and your terminals within reach. Tessera brings Claude Code and Codex sessions
Related Agents
Colab Runner
Executes GPU work on a Colab runtime from this terminal with the Colab CLI — provisions the accelerator, clone
Failure Intake
Use this agent FIRST when the user brings failing Playwright tests to debug — raw terminal output, a reports/r
Forager
External research bee (the Forager in Hive). Given a scoped external question, ranges outside the hive — docum