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 perceptiongit 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/perception)<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/perception"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/perception/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/perception"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/perception.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 | $0.00103 | $0.00778 |
| Opus 5 | $0.00051 | $0.00389 |
| Sonnet 5 | $0.00021 | $0.00156 |
| Haiku 4.5 | $0.00010 | $0.00078 |
Grade A, and why
perception 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 7d 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.
Perception
Notice what is actually there, especially the details everyone else missed.
What This Skill Does
In D&D, Perception is the raw ability to notice things: the hidden door, the faint sound, the detail that does not belong. Unlike Investigation (which follows evidence methodically) or Insight (which reads subtext), Perception is about the initial act of noticing. The real-world version is detail-catching: spotting the typo in the contract, the anomaly in the dashboard, the one metric that moved when it should not have, the thing that is present but no one is looking at. In this grimoire, Perception is treated as a metaphorical skill with a shipping-now delivery profile. Canonical reference input: Perception (skill).
When To Use
- You need a fresh pair of eyes on something — a document, dashboard, codebase, or design — to catch what is being overlooked.
- Something feels off but you cannot articulate what. You need systematic observation to find the anomaly.
- A review or audit needs to prioritize what to look at: where are the details most likely to matter?
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.
- Scan the full surface: read the whole thing, not just the parts that seem important.
- Flag anomalies: anything that does not pattern-match with its surroundings. Typos, inconsistencies, outlier values, broken symmetries.
- Rank by consequence: which noticed details actually matter vs. which are cosmetic?
- Deliver the perception report: what was noticed, why it stands out, and whether it warrants action.
- Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.
Deliverables
- A list of noticed anomalies, inconsistencies, or overlooked details ranked by likely consequence.
- For each finding: why it stands out and whether it requires action or is merely notable.
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.
- 7d ago First seen · 66 lines · 103 tokens per session scan A 20325a9cde69
perception 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 103 tokens to every session and 778 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.
Other skills, from other repositories
review-agent
Use when reading code changes with adversarial intent to find bugs, security holes, logic errors, and performance traps.
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"…
workspace-diff-review
Reviews the current workspace diff with a pre-landing mindset.
code-review-skill
Reviews code for bugs, inefficiencies, and adherence to best practices, providing actionable improvement suggestions.
generic-code-reviewer
Review code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Supports any tech stack - HTML/CSS/JS, React, TypeScript, Node.js, Python, NestJS, Next.js, and more. Use when completing features, before commits, or reviewing pull requests.
coding
Use when five specialized coding agents (linter, perf, refactor, security, test) that enforce quality gates across the development lifecycle. From lint enforcement through performance profiling, refactoring, security auditing, and test coverage. Use when working with coding agents.