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.
npx skills add Hmbown/Wizards-of-the-Ghosts --skill hold-monstergit clone --depth 1 https://github.com/Hmbown/Wizards-of-the-GhostsWrote 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.
[](https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/hold-monster)<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/hold-monster"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/hold-monster/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.
<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/hold-monster"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/hold-monster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.00688 |
| Opus 5 | $0.00034 | $0.00344 |
| Sonnet 5 | $0.00014 | $0.00138 |
| Haiku 4.5 | $0.00007 | $0.00069 |
Grade A, and why
hold-monster 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hold Monster
Freeze a large-scale system or service as an emergency circuit breaker.
What This Skill Does
Hold Monster is Hold Person scaled to larger targets. The real-world version is the emergency circuit breaker: halting an entire service, freezing a deployment pipeline, or stopping a runaway process at the infrastructure level. This is the big red button — it stops everything, and it should only be pressed when the alternative is worse. In this grimoire, Hold Monster is treated as a hybrid spell with a prototype delivery profile. Canonical reference input: Hold Monster (spell).
When To Use
- A system-wide emergency requires an immediate halt: runaway costs, cascading failures, or data integrity threats.
- You need to design a circuit breaker or emergency stop mechanism for a large-scale system.
Prerequisites
- No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session.
Procedure
- Restate the target, the success condition, and any no-touch boundaries before taking action.
- Assess the emergency: what is happening, how fast, and what is the blast radius if unchecked?
- Determine the freeze scope: what can be stopped safely vs. what must keep running even in an emergency.
- Activate the circuit breaker with explicit logging and notification.
- Define the recovery plan: how to restore service safely after the emergency is resolved.
- Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.
Deliverables
- A circuit breaker specification: what stops, what stays running, and what triggers the halt.
- A recovery plan: step-by-step restoration procedure after the emergency.
Pitfalls / Guardrails
- Call out the glue, permissions, or missing infrastructure before you imply this is fully operational.
- Circuit breakers are for genuine emergencies. Do not use system-wide halts for problems that can be solved with targeted intervention.
- Every circuit breaker must have a recovery plan. Stopping a system without knowing how to restart it is not safety — it is a different kind of failure.
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.
- 9d ago First seen · 66 lines · 68 tokens per session scan A f50260b1b3bf
hold-monster 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 68 tokens to every session and 688 once invoked, about $0.0003 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.
Other skills, from other repositories
pipedream-workflows
Use when pipedream serverless workflows — triggers, code steps, pre-built actions, data stores, HTTP. Use when working with pipedream workflows.
flow-nexus-swarm
Cloud-based AI swarm deployment and event-driven workflow automation with Flow Nexus platform.
reproduce
Reproduce a cloudflare/agents GitHub issue by scaffolding a minimal Agents/Worker project and deploying it to a temporary Cloudflare account, then report findings back on the issue.
event-driven-architecture
Kafka, RabbitMQ, SQS/SNS, event sourcing, CQRS, saga patterns, dead letter queues, and idempotency. Use when designing asynchronous systems, implementing message-driven workflows, or building event streaming pipelines.
devops-cloud
DevOps, cloud infrastructure, and platform engineering. Use when working with AWS, GCP, Azure, Kubernetes, Terraform, CI/CD pipelines, or infrastructure as code.
edge-computing
Edge computing with Cloudflare Workers, Deno Deploy, Bun, Vercel Edge Functions, AWS Lambda@Edge, and edge databases (Turso, D1, DynamoDB Global Tables). Use when building low-latency edge applications, edge-side rendering, or globally distributed compute.