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 thunderwavegit 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/thunderwave)<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/thunderwave"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/thunderwave/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/thunderwave"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/thunderwave.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 | $0.00026 | $0.00581 |
| Opus 5 | $0.00013 | $0.00291 |
| Sonnet 5 | $0.00005 | $0.00116 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
thunderwave 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 8d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thunderwave
Trigger a dramatic, high-impact action through a tightly gated device, webhook, or automation.
What This Skill Does
Use this skill for intentionally theatrical or forceful actions, but only behind explicit confirmation and a hard safety boundary. In this grimoire, Thunderwave is treated as a literal spell with a prototype delivery profile. Canonical reference input: Thunderwave (spell).
When To Use
- You want a visible real-world effect such as lights, sounds, signage, or a controlled automation burst.
- A dramatic action is part of the experience, demo, or ritual.
- The blast radius is known and the target surface is intentionally prepared.
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.
- Identify the target device, webhook, or effect surface.
- Require explicit confirmation of the payload, boundary, and rollback plan.
- Trigger the effect through the narrowest possible integration.
- Report exactly what fired and whether rollback is available.
- Stop for explicit confirmation before taking a live action that changes access, triggers an alert, or touches a real system boundary.
- Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.
Deliverables
- A precise execution plan or payload.
- A clear confirmation checkpoint.
- A rollback or shutdown path when one exists.
Pitfalls / Guardrails
- Call out the glue, permissions, or missing infrastructure before you imply this is fully operational.
- Never improvise on unverified device integrations or dangerous automations.
- Refuse actions that create real-world safety hazards or uncontrolled side effects.
Verification
- Check that the result includes every deliverable promised above.
- Check that confirmed facts, assumptions, and inferences are visibly separated.
- Check that the exact live target, confirmation gate, and rollback or recovery path are explicit.
- Check that any missing glue code, permissions, or future work is labeled before the skill is treated as ready.
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.
- 8d ago First seen · 69 lines · 26 tokens per session scan A 056b4dadcfda
thunderwave 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 26 tokens to every session and 581 once invoked, about $0.0001 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
embedded-iot
Embedded systems firmware, microcontrollers (ESP32, STM32, Arduino, Raspberry Pi), RTOS (FreeRTOS, Zephyr), IoT protocols (MQTT, CoAP, BLE), bare-metal C/C++, and hardware peripheral interfaces (I2C, SPI, UART, GPIO). Use when developing firmware, working with microcontrollers, or building IoT devices.
hr-embedded
Help HR and recruiting teams hire and assess embedded systems engineering candidates (firmware, RTOS, hardware-software integration). Use when asked to write an embedded engineer job description, create firmware interview questions, assess an embedded candidate, build an embedded engineering leveling framework, or…
code-research
Use when produce structured understanding of unfamiliar codebases — architecture, data flows, dependencies, and conventions. Use when joining a new project, tracing feature implementations, or mapping system architecture.
autogen-agents
Use when autoGen multi-agent conversations — AssistantAgent, UserProxyAgent, group chat, code execution. Use when working with autogen agents.
code-agent
Use when implementing features from specs — reads requirements, writes code with tests, iterates until verification passes.
deploy-agent
Use when ship code through controlled pipeline with verification gates and rollback plans.