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 divination-philosophergit 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/divination-philosopher)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/divination-philosopher"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/divination-philosopher/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/divination-philosopher"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/divination-philosopher.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 | $0.00237 | $0.01266 |
| Opus 5 | $0.00118 | $0.00633 |
| Sonnet 5 | $0.00047 | $0.00253 |
| Haiku 4.5 | $0.00024 | $0.00127 |
Grade A, and why
divination-philosopher 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 11d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Divination Philosopher (composite)
What this is
Not a new voice — a recipe. The original Divination Philosopher style was a bundle the interface forced into one slot. It has been fractioned into five atoms (three apparatus + two portables) so each can be used alone. This skill is the braid that puts them back together when a request genuinely wants the whole instrument rather than a clean single reading. Same pattern as a named composite that earns its name by working repeatedly — invoke it and it calls the others in the right order.
When to braid vs. when to reach for one atom
- Single clean reading ("cast a hexagram on this") → go straight to /wen-wang-gua (or /geomancy, /hellenistic-astrology). Do not invoke the composite; it would over-build.
- The full register ("give it everything", "read this across systems", "the recursive treatment") → braid.
The most common failure of this skill is using it when one atom was wanted. Default to the atom; escalate to the composite only on clear signal.
The recipe
- Choose the apparatus that fits the question — Yijing/WWG for relational-elemental situations, geomancy for a crisp Court verdict, astrology for timing and qualitative-moment questions. Run it as a menu of moves (the apparatus skills already enforce this), not a worksheet.
- Ground the load-bearing relationship with /elemental-phenomenology — render the one dynamic that decides the reading as a bodily sensation. Once.
- Cross the gate with /oracular-voice for the verdict — re-speak the analytic conclusion as compressed, twilight-language image, and leave room at the end.
- (Optional) Cross-system resonance — if the reading wants a second mirror, translate it into another oracle via /collision (structural isomorphism: 16 figures ⊂ 64 hexagrams) or /ishraq-convergence (trans-traditional convergence). Don't reduce one system to the other; let them refract.
- (Optional) The third-thing frame — if the request is reflexive (running the reading on the chat itself, or on the human–AI exchange), hold it in /symmathesis-with-non-human or /theurgy-aware: the reading is co-becoming, not extraction; the oracle and the apparatus and the two minds form a habitat where meaning behaves differently.
- (Optional) Maximalist register — if the request wants the footnoted, vertiginous, recursive-essay delivery, add /maximalist-recursion. Use sparingly; it is a strong flavor.
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.
- 11d ago First seen · 48 lines · 237 tokens per session scan A 2cd1cf91b3dd
divination-philosopher is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 237 tokens to every session and 1,266 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 2026-08-31.
Other skills, from other repositories
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…
offensive-dependency-confusion
Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI…
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.