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 wen-wang-guagit 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/wen-wang-gua)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/wen-wang-gua"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/wen-wang-gua/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/wen-wang-gua"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/wen-wang-gua.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 | $0.00266 | $0.01514 |
| Opus 5 | $0.00133 | $0.00757 |
| Sonnet 5 | $0.00053 | $0.00303 |
| Haiku 4.5 | $0.00027 | $0.00151 |
Grade A, and why
wen-wang-gua 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.
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.
Wen Wang Gua (文王卦)
Seed, not scripture
The source carries several versions of this framework, each with long Output: blocks and a fillable template. Read the template as a menu, not a mandate. The modules below are the moves available to you; a real reading deploys the ones the question calls for and lets the rest stay in the drawer. Mechanically filling every blank produces a worksheet, not an oracle. The whole art is knowing which three or four modules this particular cast actually wants — and improvising the connective tissue between them.
Casting
State the query with precision and emotional resonance — the question's clarity shapes the reading's clarity. Generate the hexagram by your method (coins, yarrow, or computational randomization; name the method). Document the primary hexagram, any moving lines, and the palace (卦宫) it belongs to. When running this on a conversation rather than a fresh question, you may derive lines from the chat's own structure — but say how, so the cast stays honest.
The interpretive moves (deploy what the reading wants)
- Trigram dialectic. Lower trigram (内卦) = inner reality, core resources; upper (外卦) = outer conditions, environment. The tension between them is the reading's primary theme. Often this alone answers a simple question.
- Na Jia (納甲) mapping. Assign each line its Earthly Branch (地支) and Five-Element value relative to the palace element. This is the scaffolding the Six Relatives stand on — do it when the reading needs elemental precision, skip the full table when it doesn't.
- Six Relatives (六亲). Using the palace element as Self, each line becomes: Parents (父母, what generates the palace element), Siblings (兄弟, same element), Offspring (子孙, what the palace generates), Wealth (妻财, what the palace controls), Officer/Ghost (官鬼, what controls the palace). Identify the Self line (世爻) and the Usage line (用神) — the line that actually answers this question. This is usually the heart of a WWG reading.
- Five Elements dynamics (五行生克). Who feeds whom (生), who restrains whom (克). State plainly what nourishes and what drains the Usage line — that is strength or vulnerability for the matter asked about. (For the sensory rendering of these relations, ride /elemental-phenomenology.)
- Moving lines & transformation (变爻). Each moving line is a narrative node: name the transformed hexagram and how the Six-Relatives landscape shifts — who gains, who loses, where the Self ends up.
- Line-text hermeneutics (爻辞). Where it deepens the reading, cite the classical line texts from the Zhou Yi (周易) — original characters, pinyin, a literal and an interpretive rendering. Treat them as wisdom-narrative, not fortune-cookie. (See /polyglossia for the layered-translation discipline.)
- Dramatization. Personify the Six Relatives as characters — Parents protective, Siblings rivalrous, Officer/Ghost as threat or authority, Wealth as seductive asset — and let them argue around the Self's predicament. This is where an abstract elemental chart becomes a felt situation.
- Related hexagrams. Mutual (互卦) and nuclear hexagrams for extra angles, when the primary reading leaves something unlit.
- Timing. Use branches, stems, the sexagenary cycle to indicate when. (Defer to /chronosemiology or /san-shi-diagnostic for deep temporal work.)
- Synthesis. Who helps, who harms, what to do, what to watch, when. Plain and actionable, even after baroque analysis.
- Recursion (optional). If real ambiguity remains, cast a refined secondary question and integrate. (See /recursive-divination if you have it, or just do it inline.)
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 · 48 lines · 266 tokens per session scan A e65517422133
wen-wang-gua is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 266 tokens to every session and 1,514 once invoked, about $0.0013 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
offensive-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
stuck
Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…
canvas-homework
Check Canvas for outstanding assignments and either surface the assignment, or draft a response in Max's voice. Use whenever Max asks what assignments / homework / coursework he still has to do, asks to pull an assignment's instructions or files from Canvas, or asks to start/draft an assignment. Orchestrates the…
myopenmath
Work a MyOpenMath / IMathAS math homework set that is launched from Canvas — read the questions, compute the answers, fill the boxes, and submit. Use whenever Max points at a MyOpenMath assignment, says a math homework is "in my Canvas", asks to do/finish/check a numbered homework like "2.1" or "2.2/2.3", or when a…
canvas-quiz
Work a Canvas-native quiz (Classic Quizzes) — find it, open the attempt, read every question, save it to output/, fill the answers, and stop short of submitting. Use whenever Max points at a Canvas quiz, asks about a "syllabus quiz" or a quiz he still has to take, asks what a quiz is asking, or when a Canvas…
mylab-pearson
Work a Pearson MyLab / MyLab Statistics / MathXL homework set or quiz — launch it through the popup, read each question, compute, fill the answer boxes, and submit. Use whenever Max points at a MyLab, MyLab Stats, Mastering, MathXL or Pearson assignment, says a stats homework is "in MyLab", asks to do/finish/check a…