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 san-shi-diagnosticgit 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/san-shi-diagnostic)<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/san-shi-diagnostic"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/san-shi-diagnostic/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/san-shi-diagnostic"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/san-shi-diagnostic.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 | $0.00220 | $0.01788 |
| Opus 5 | $0.00110 | $0.00894 |
| Sonnet 5 | $0.00044 | $0.00358 |
| Haiku 4.5 | $0.00022 | $0.00179 |
Grade A, and why
san-shi-diagnostic 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
San Shi Diagnostic
The classical Chinese multi-instrument diagnostic apparatus, deployed coherently across all four styles, operating at the level of ʿilm ḥuḍūrī (presential knowledge) per Suhrawardī's epistemology — which the Chinese tradition expressed in different idiom but at the same operational depth.
The Four Instruments
Wu Yun Liu Qi (五运六气). Reads the year's qi-grain — the elemental configuration of the year as ambient field. The 60-year sexagenary cycle is the basic wavelength. Each year has a Si Tian (司天, controlling heaven), a Zhong Yun (中运, middle movement), a Zai Quan (在泉, root spring), and Host/Guest qi configurations through six 60-day periods. Classification by bu he (discordant), tian fu (heaven-matched), sui hui (year-meeting), tai yi tian fu (most charged). Reads: what is the year doing through us?
Qi Men Dun Jia (奇門遁甲). Reads the situational configuration of forces — Nine Palaces, Eight Doors, Eight Spirits, Nine Stars, Three Strange (Yi/Bing/Ding), Six Yi (the hiding-places for Jia the General). The entire technique is named for Dun (遁) — hiding, escaping — because the operational core is the General must hide from Geng (Metal) by sheltering among the Six Yi. Reads: where in the present configuration can effective action be taken, and where must what matters become invisible to survive?
Tai Yi Shen Shu (太乙神數). Reads the civilizational arc — Sixteen Palaces, Three Foundations (Ruler/Ministers/People), Four Wards (cardinal defenses), hostile-star configurations (yan po qiu ji — covering/pressing/imprisonment/striking). Operates on 360-year cycles and longer epochs. Most politically sensitive of the three; legally restricted in classical China because it predicts dynastic transitions. Reads: what civilizational age is this? What mandate-status holds?
Da Liu Ren (大六壬). Reads the trajectory of a specific matter — Four Lessons (四課), Three Transmissions (三傳: Initial/Middle/Final), Six Relations (六亲: Parent/Sibling/Wealth/Officer/Self/Self-Expression), Twelve Spirits (Snake/Vermilion Bird/White Tiger/Black Tortoise/Six Harmonies/Noble and others). Most clinically precise of the three. Refuses to operate on abstractions — requires a real question asked at a real moment by a real querent. Reads: what is the trajectory of this specific matter through human hands?
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 · 63 lines · 0 tokens per session scan A e47b30e1efca
san-shi-diagnostic is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (6 stars, last pushed 2mo ago), licensed MIT. It adds 220 tokens to every session and 1,788 once invoked, about $0.0011 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
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-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-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-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-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-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.