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 confusiongit 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/confusion)<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/confusion"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/confusion/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/confusion"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/confusion.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 | $0.00065 | $0.00651 |
| Opus 5 | $0.00032 | $0.00326 |
| Sonnet 5 | $0.00013 | $0.00130 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
confusion 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.
Confusion
Generate controlled chaos to stress-test a system's resilience.
What This Skill Does
Confusion makes targets act randomly and unpredictably. The real-world version is chaos engineering: injecting controlled randomness, unexpected inputs, and edge cases to discover how systems behave when things go wrong. This is fuzzing, monkey testing, and the art of breaking things on purpose so they do not break by accident. In this grimoire, Confusion is treated as a metaphorical spell with a shipping-now delivery profile. Canonical reference input: Confusion (spell).
When To Use
- You want to stress-test a system, API, or workflow with unexpected inputs and edge cases.
- A process works perfectly under ideal conditions and you need to know how it fails under chaos.
- You need to generate adversarial test cases, random inputs, or edge-case scenarios.
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 system, API, workflow, or process to stress-test.
- Generate a set of chaotic inputs: edge cases, malformed data, race conditions, unexpected sequences.
- Predict how each chaotic input should be handled (graceful degradation, error, recovery).
- Deliver the chaos test suite with expected vs. worst-case outcomes for each scenario.
- Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.
Deliverables
- A chaos test suite: specific adversarial inputs, edge cases, and unexpected scenarios.
- Expected behavior for each scenario: how the system should handle it vs. how it might fail.
Pitfalls / Guardrails
- Keep the metaphor anchored to a real mechanism instead of drifting into lore.
- Chaos must be controlled. Always define blast radius and rollback procedures before injecting randomness.
- Do not generate chaos for production systems without explicit safety gates and authorization.
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 · 65 tokens per session scan A 2944772ad68a
confusion 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 65 tokens to every session and 651 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
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
qa-investigation
Investigate a specific test failure to its root cause and document the why. Detects whether a failing test is flaky (intermittent) or a deterministic bug during reproduction. Use when a test fails and you need the real cause, not just to make it green. Execution layer, not strategy review. Keywords: flaky test…
linter-agent
Use when detecting and fixing code style violations, enforcing project conventions, ensuring consistent formatting.
perf-agent
Use when measure before optimizing, target actual bottlenecks proven by profiling, verify with benchmarks.
test-agent
Use when writing comprehensive test suites covering happy paths, error paths, edge cases, and integration points.
benchmark-before-optimize
For performance work: measure before changing, profile to find bottlenecks, compare before and after.