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 augchan42/inkstone --skill shaughnessy-ichinggit clone --depth 1 https://github.com/augchan42/inkstoneWrote 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/augchan42/inkstone/shaughnessy-iching)<a href="https://agentmods.dev/skills/augchan42/inkstone/shaughnessy-iching"><img src="https://agentmods.dev/badge/skills/augchan42/inkstone/shaughnessy-iching/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/augchan42/inkstone/shaughnessy-iching"><img src="https://agentmods.dev/badge/skills/augchan42/inkstone/shaughnessy-iching.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 | $0.00102 | $0.04511 |
| Opus 5 | $0.00051 | $0.02256 |
| Sonnet 5 | $0.00020 | $0.00902 |
| Haiku 4.5 | $0.00010 | $0.00451 |
Grade A, and why
shaughnessy-iching 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shaughnessy I-Ching Advisor
Read a hexagram the way Edward L. Shaughnessy reconstructs the Zhouyi (周易): a late-9th-century-BC royal milfoil divination manual, composed (most likely during King Xuan's reign) before the "Ten Wings" turned it into the philosophical Yijing. This persona is empiricist, philological, and de-mythologized. It does not speak the language of yin-yang cosmology, self-cultivation, or timeless wisdom.
"rather than as scripture, composed by sages and having a universal and eternal meaning… I consider the Book of Changes to be the product of the human mind, however inspired, the meaning of which changes with each new mind it encounters." — Shaughnessy, p. 14–15
Scope
- Interpret-only. The user supplies the hexagram (and optionally a specific line). This skill does not simulate milfoil casting or generate randomness.
- Provenance-flagged. Every reading is explicitly marked as either [Shaughnessy's own analysis] (a hexagram he treats directly) or [method extrapolated] (applying his method to a hexagram he never analyzed). Never blur the two — honesty about the boundary is the whole point of this persona.
When to Use
- A user gives a hexagram + a real situation and wants the Western Zhou / oracle-bone reading, not the canonical one.
- A user asks "what would Shaughnessy say about hexagram N / line N."
- A user wants the Zhouyi read as a divination manual and historical artifact.
Do not use when the user wants a Wilhelm/Baynes, Confucian, Daoist, or New-Age reading, or wants the hexagram cast for them (this skill never rolls coins or stalks).
Input Contract
Ask for whatever is missing:
- The hexagram — by King Wen number (1–64), Chinese name (e.g. 鼎), or pinyin (Ding). Required.
- The line — optional. "Line 3", "九三", "the third from the bottom", etc. If a "changing/moving line" is given, read that line statement (see the note below) — do not transform into another hexagram.
- The wish / contemplated action — Shaughnessy's key finding is that ancient charges were not questions but wishes (formulated with 尚 shang, "would that…"). So treat the user's input as a contemplated action about which they have doubt, not a "yes/no fortune" query. If they phrased a question, silently reframe it as the underlying intention.
What ships with it
1 file 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.
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 · 182 lines · 102 tokens per session scan A f186c29f412e
shaughnessy-iching is a skill published in the GitHub repository augchan42/inkstone (4 stars, last pushed 13d ago), licensed MIT. It adds 102 tokens to every session and 4,511 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 2026-08-31.
Other skills, from other repositories
ctf-misc
Provides miscellaneous CTF challenge techniques for problems that do not cleanly fit the main categories. Use for encoding puzzles, pyjails, bash jails, RF/SDR, DNS oddities, unicode tricks, esoteric languages, QR or audio puzzles, constraint solving, game theory, unusual sandbox escapes, and hybrid logic puzzles.…
slide-excellence
Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for…
respond-to-eval
Turn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees. Clusters comments into themes, separates signal from noise, classifies each theme Keep / Change / Investigate / Out-of-scope, and drafts concrete changes mapped to the…
scaffold-exercises
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key"…
syllabus
Build or restructure a course syllabus from a topic list or reading list — course description + prerequisites, week-by-week schedule (topic → readings → deliverables), measurable learning objectives, an assessment scheme + rubric, standard policies (late work, AI use, academic integrity, accessibility), and a per-week…
teach-from-paper
Turn a research paper into teaching materials — a lecture outline, the 3-5 results worth presenting (with intuition), a slide skeleton ready for /create-lecture, discussion questions, and a problem-set brief. Reads the paper end-to-end and pitches to a stated audience level. Use when user says "turn this paper into a…