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 investigationgit 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/investigation)<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/investigation"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/investigation/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/investigation"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/investigation.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 | $0.00023 | $0.00490 |
| Opus 5 | $0.00012 | $0.00245 |
| Sonnet 5 | $0.00005 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
investigation 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.
What it actually says
Investigation
Follow evidence through a system until the hidden mechanism becomes legible.
What This Skill Does
Use this skill when a problem has clues, but they need to be connected into a causal explanation. In this grimoire, Investigation is treated as a metaphorical skill with a shipping-now delivery profile. Canonical reference input: Investigation (skill).
When To Use
- You are debugging a failure, regression, or strange behavior.
- There are logs, traces, docs, or code clues that need synthesis.
- You need the why, not just the what.
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.
- Collect the strongest observable clues first.
- Test causal hypotheses against code, data, logs, or configuration.
- Eliminate weak explanations and keep the chain of reasoning tight.
- Return the most defensible explanation plus the next decisive check.
- Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.
Deliverables
- A ranked set of causes with evidence.
- The most likely root cause.
- A next-step validation or fix path.
Pitfalls / Guardrails
- Keep the metaphor anchored to a real mechanism instead of drifting into lore.
- Do not confuse correlation with cause.
- Keep evidence and inference visibly separate.
Verification
- Check that the result includes every deliverable promised above.
- Check that confirmed facts, assumptions, and inferences are visibly separated.
- Check that the metaphor still maps cleanly to a real operational mechanism.
Example Invocation
/investigation follow the clues here and tell me the most likely root cause with evidence
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 · 67 lines · 23 tokens per session scan A 63a020bfd75a
investigation 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 23 tokens to every session and 490 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
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.
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
systematic-debugging
Structured debugging methodology — use before proposing fixes for any error or failure. Covers: code bugs, build errors, deploy failures, config conflicts, dependency issues, infra problems. Also use when previous fix attempts failed or root cause is unclear.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
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.