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 faerie-firegit 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/faerie-fire)<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/faerie-fire"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/faerie-fire/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/faerie-fire"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/faerie-fire.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 | $0.00062 | $0.01060 |
| Opus 5.5 | $0.00025 | $0.00424 |
| Sonnet 5.5 | $0.00012 | $0.00212 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
faerie-fire 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Faerie Fire
Make hidden things visible by highlighting, tagging, and marking them for attention.
What This Skill Does
Faerie Fire marks things that are already known. It does not search, discover, explain, translate, or fix. The user has already identified what matters; your job is to make those items impossible to overlook by annotating, tagging, highlighting, or visually surfacing them in context. In this grimoire, Faerie Fire is treated as a metaphorical spell with a shipping-now delivery profile. Canonical reference input: Faerie Fire (spell).
When To Use
- "Highlight", "tag", "mark", "annotate", "call out", "flag" applied to specific items the user has already named or located
- "Make X visible" where X is a known set of findings, clauses, functions, tickets, or features
- "Show me where [specific thing] appears" — location surfacing, not discovery
- "Annotate", "add margin notes", "color-code", "produce a summary table of marked items"
- The user provides the target list and asks you to apply markers to a document, codebase, dataset, or diagram
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.
- Confirm the target set: Restate what the user wants marked. If the list is implicit, extract it explicitly before annotating.
- Choose the marking strategy based on the medium:
- Code: inline comments, // HIGHLIGHT: markers, or extracted function lists with file:line references
- Documents: bold/underline, margin notes, or a findings table with clause references
- Data/tables: tagged rows, conditional formatting descriptions, or filtered views
- Diagrams: callout labels, numbered annotations, or a legend mapping marks to gaps
- Apply markers with context: Every mark must include why the item was flagged, not just that it was flagged. A marker without rationale is noise.
- Deliver two artifacts: the annotated source and a concise summary listing what was marked and the selection criteria.
- Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.
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.
- 1mo ago First seen · 79 lines · 62 tokens per session scan A 049e4d932c59
faerie-fire is a skill published in the GitHub repository Hmbown/Wizards-of-the-Ghosts (112 stars, last pushed 6mo ago), licensed CC0-1.0. It adds 62 tokens to every session and 1,060 once invoked, about $0.0002 per session on Opus 5.5. 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
hr-employee-experience
Help HR business partners, employee experience managers, and people leaders understand, design, and run employee experience strategies, journey mapping, engagement programs, culture diagnostics, onboarding and offboarding experience design, workplace environment initiatives, and recognition and belonging programs. Use…
hr-uiux
Help HR managers, recruiters, and talent acquisition teams understand UI/UX Design, Product Design, Design Systems, User Research, Interaction Design, and modern digital product design workflows. Use when asked to explain UI/UX, screen product designers, understand UX research, compare UI and UX, evaluate design…
hr-design-thinking
Help HR teams and people leaders apply design thinking to HR challenges, including employee experience design, HR service redesign, journey mapping, and human-centered HR solution development. Use when asked to apply design thinking to HR, run an HR design sprint, apply design thinking to map the employee journey…
baoyu-infographic
An infographic generator that turns information into visual summaries using different layouts and visual styles. It supports many combinations for arranging and presenting the content.
baoyu-diagram
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system…
json-canvas
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.