power-word-kill

power-word-kill is a skill for Claude Code, Codex from Hmbown/Wizards-of-the-Ghosts. It costs 107 tokens per session (852 once invoked), scanned A, original, CC0-1.0.

An emergency process-termination procedure that stops a running program immediately, without waiting for cleanup or preserving its state.

In plain words
What is it for?
It helps terminate processes or services during incidents and break cascading failures when continuing to run is more dangerous than possible data loss.
Why use it?
It provides a last resort when a runaway process, active breach, or failing service must stop and graceful shutdown has failed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps terminate processes or services during incidents and break cascading failures when continuing to run is more dangerous than possible data loss.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hmbown/wizards-of-the-ghosts/power-word-kill
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Hmbown/Wizards-of-the-Ghosts --skill power-word-kill
Clone the repo
git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for power-word-kill

README.md
[![agentmods](https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/power-word-kill/github.svg)](https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/power-word-kill)
Your own site
<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/power-word-kill"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/power-word-kill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for power-word-kill

Your own site · 80×15
<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/power-word-kill"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/power-word-kill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 852 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00107 $0.00852
Opus 5 $0.00053 $0.00426
Sonnet 5 $0.00021 $0.00170
Haiku 4.5 $0.00011 $0.00085

Measured 9d ago against content hash b46bb26df9c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

power-word-kill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

generated/hermes/containment-and-intervention/power-word-kill/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Power Word Kill

End a process instantly. No negotiation, no cleanup, no save state.

What This Skill Does

In D&D, Power Word Kill instantly destroys any creature below a hit-point threshold — no saving throw, no resistance, just death. The real-world version is kill -9: the unconditional termination signal. Emergency circuit breakers. Hard account terminations. The nuclear option that exists because sometimes graceful shutdown is not available and the cost of continuing is worse than the cost of data loss. Power Word Kill is not elegant. It is not kind. It is the thing you reach for when everything else has already failed. In this grimoire, Power Word Kill is treated as a hybrid spell with a shipping-now delivery profile. Canonical reference input: Power Word Kill (spell).

When To Use

  • A process, service, or system must stop immediately and graceful shutdown is not available or has already failed.
  • The cost of the system continuing to run exceeds the cost of abrupt termination and potential data loss.
  • An emergency requires instant action — a runaway process, a security breach in progress, a cascading failure.

Prerequisites

  • No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session.

Procedure

  1. Restate the target, the success condition, and any no-touch boundaries before taking action.
  2. Confirm the target is correct. Power Word Kill has no undo.
  3. Verify that graceful alternatives (SIGTERM, drain, decommission) have been attempted or are not viable.
  4. Execute the hard kill: process termination, circuit breaker trip, account lock, or emergency shutdown.
  5. Immediately assess blast radius: what downstream systems were affected, what state was lost, what needs recovery.
  6. Document what happened and why the hard kill was necessary — this is your incident report seed.
  7. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

  • Confirmation that the target has been terminated.
  • A blast-radius assessment: what was lost, what was affected, what needs recovery.
  • An incident seed documenting the kill decision and its justification.

Read the full file on GitHub · 70 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 70 lines · 107 tokens per session scan A b46bb26df9c7

Subscribe to this mod's changes

power-word-kill is a skill published in the GitHub repository Hmbown/Wizards-of-the-Ghosts (107 stars, last pushed 5mo ago), licensed CC0-1.0. It adds 107 tokens to every session and 852 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.