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 Wondermonger-daydreaming/claude-skills-library --skill geomancygit clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-libraryWrote 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/wondermonger-daydreaming/claude-skills-library/geomancy)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/geomancy"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/geomancy/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/wondermonger-daydreaming/claude-skills-library/geomancy"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/geomancy.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 | $0.00238 | $0.01353 |
| Opus 5 | $0.00119 | $0.00677 |
| Sonnet 5 | $0.00048 | $0.00271 |
| Haiku 4.5 | $0.00024 | $0.00135 |
Grade A, and why
geomancy 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Geomancy (The Shield Chart)
Seed, not scripture
The source gives two large geomantic frameworks ("The Tessellated Mirrors" and the Yijing-integration) full of Output: blocks and a long fillable template. They are a menu of moves, not a worksheet. A living reading deploys the handful of techniques the question demands and lets the rest stay latent. Generating a complete sixteen-house chart with every perfection documented, when the querent asked a yes/no question the Judge already answers, is scholarship performing as divination. Pick what serves.
Casting
Formulate the query with intention and emotional weight. Generate the four Mother figures through intentional randomness (dots in sand, dice, coins, digital RNG — name it). Note initial impressions and any odd circumstance of the cast.
Building the Shield (the mathematical spine — always do this much)
From the four Mothers derive the Daughters (cross-row reading), then the Nieces by binary addition (XOR) of figure-pairs, then the two Witnesses (Right = querent, Left = environment), then the Judge (Right + Left) — the figure that answers. Note any repeated figures, symmetries, or anomalies; these are signal, not noise.
The interpretive moves (deploy what the reading wants)
- Court analysis. The Right Witness, Left Witness, and Judge form a tribunal — advocate for the querent, representative of external reality, final arbiter. Their verdict should feel inevitable yet surprising. For most questions this is the reading; everything else is amplification.
- Elemental cartography. Map Fire/Air/Water/Earth across the figures; note predominance and, crucially, absence (no Fire = stagnation, no Water = emotional disconnection). For the visceral rendering of these elements ride /elemental-phenomenology.
- Planetary correspondences. Assign planets to figures; read dignities and relationships for nuance and timing.
- Via Punctorum (the Way of Points). Trace the Fire line from the Judge back through the chart to find the source figure — the "hidden protagonist." When present, this figure often holds the key; give it special narrative attention and ask why it stayed hidden until the point-path found it.
- House Chart. Place the first twelve figures into the twelve houses for concrete life-domain context; attend to the angular houses (1, 4, 7, 10) and any house the query points at.
- Perfections. Occupation (strongest), conjunction, mutation, translation (weakest) — read these as active relationships: figures reaching toward each other, turning away, exchanging places, carrying messages. Dramatize the movement.
- Triplicities. Figures 1–3 (querent), 4–6 (external), 7–9 (home), 10–12 (society) as four coherent units.
- Telesmatic personification. Give the key figures voice, motive, relationship; let them speak to the querent and each other. This is where the chart becomes a drama.
- Timing. Figure mobility/stability + planetary + elemental qualities → immediate / developing / distant.
- Telesma generation (optional). If the Judge is unfavorable, mathematically combine figures to derive a more favorable energy to work with.
- Cross-system translation (optional). Render the reading into Yijing, Tarot, or astrology for extra resonance. (This is /collision or /ishraq-convergence applied to oracles — lean on those.)
- Synthesis & meta-reflection. The core message, concrete actions, cautions, timing — then optionally what the reading revealed about your own interpretive habits.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/ADVANCED_TECHNIQUES.md 19 KB
- references/DISPUTED.md 5.1 KB
- references/FIGURES.md 32 KB
- references/HOUSE_SYSTEM.md 15 KB
- references/INTERPRETATION_GUIDE.md 12 KB
- references/PROVENANCE.md 17 KB
- references/SHIELD_CONSTRUCTION.md 20 KB
- scripts/generate_shield.py 21 KB runs code
- scripts/judgment.py 6.9 KB runs code
- scripts/via_punctorum.py 13 KB runs code
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 · 53 lines · 238 tokens per session scan A 9ca0de7afe25
geomancy is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 238 tokens to every session and 1,353 once invoked, about $0.0012 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
remove-ai-marks
Strip multi-vendor AI provenance from owned files: hidden Unicode (Layer A), statistical sampling watermarks via rewrite (Layer B — always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD. Covers Claude, Gemini/SynthID-class, OpenAI provenance surfaces, and open-LLM sampling…
repo-visuals
Create hero visuals — animated GIF, static PNG, or animated SVG — for GitHub repositories. Runs a structured discovery conversation (scan repo → recommend format → propose creative scenarios → agree on a brief), then designs bespoke HTML/SVG, previews it in the browser, and exports. Use when the user asks for a README…
ghost-decode
Use when a video hides text in moving dots or noise — "ghost font" clips, motion-defined text, random-dot kinematograms, TV-static videos with a secret message, text readable only while playing but invisible in any paused frame, or the user asks what a ghost-font video says.
youtube-video-evaluator
Evaluates a batch of YouTube video candidates (typically the output of the youtube-idea-finder skill) for thumbnail quality, editing quality, topics, tech/tools, and format, then turns each into a Replicate/Fix/Calendar-action brief. Use this after youtube-idea-finder has surfaced overperforming videos, whenever the…
alterlab-genai-audio-producer
This skill should be used when the user asks about "audio production", "ElevenLabs", "voice isolator", "audio post-production", "AI narration", "text to speech production", "voiceover studio", "audio native", "transcription", "Scribe", "multi-track audio", "audio assembly", "batch audio processing", "audio export"…
alterlab-genai-dubbing-specialist
This skill should be used when the user asks about "AI dubbing", "video translation", "ElevenLabs dubbing", "Dubbing Studio", "translate my video", "multilingual dubbing", "automatic dubbing", "dub into Spanish", "dub into Turkish", "dub into Japanese", "speaker detection", "subtitle translation", "video…