sanyuan-skills is a collection of reusable instructions, called agent skills, that extend Claude Code and other AI coding terminals with defined workflows. Developers use it for code review, learning, skill quality checks, skill creation, and organizing knowledge into wikis or study materials. The catalogue entries are individual skills from this collection.
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 sanyuan0704/sanyuan-skills --skill wiki-ingestgit clone --depth 1 https://github.com/sanyuan0704/sanyuan-skillsWrote 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/sanyuan0704/sanyuan-skills/wiki-ingest)<a href="https://agentmods.dev/skills/sanyuan0704/sanyuan-skills/wiki-ingest"><img src="https://agentmods.dev/badge/skills/sanyuan0704/sanyuan-skills/wiki-ingest/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/sanyuan0704/sanyuan-skills/wiki-ingest"><img src="https://agentmods.dev/badge/skills/sanyuan0704/sanyuan-skills/wiki-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00079 | $0.00867 |
| Opus 5 | $0.00039 | $0.00434 |
| Sonnet 5 | $0.00016 | $0.00173 |
| Haiku 4.5 | $0.00008 | $0.00087 |
Grade A, and why
wiki-ingest 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 13d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Ingest — Knowledge Base Compiler
Compile any text content (articles, documents, notes) into structured wiki pages with cross-references, building a searchable, interconnected knowledge network.
IRON LAW: One wiki page = one knowledge entity. Never cram multiple concepts into one page.
Wiki Directory Structure
Wiki defaults to wiki/ under the current project root. User may specify a different path.
wiki/
├── index.md # Full table of contents
├── log.md # Append-only operation log
├── concepts/ # Core concept pages
├── products/ # Product/tool entity pages
├── patterns/ # Engineering patterns & design decisions
└── comparisons/ # Cross-topic comparison pages
Workflow
1. Confirm Input
Accept user-specified content source:
- Pasted text directly
- File path(s) (md, txt, pdf, etc.)
- Directory path (batch processing)
If user doesn't specify a wiki path, use wiki/. Create the directory if it doesn't exist.
2. Check Existing Wiki
Read wiki/index.md (if exists) to understand existing pages and avoid duplicates.
3. Extract Knowledge Entities
Extract from content:
- Concepts (
concepts/): Abstract ideas, terminology, theories - Products (
products/): Specific products, tools, services - Patterns (
patterns/): Engineering patterns, design decisions, methodologies - Comparisons (
comparisons/): Cross-product or cross-approach analysis
Extraction threshold: An entity deserves its own page only if it would be referenced by other pages.
4. Create or Update Pages
Each entity maps to one wiki page.
→ Load references/page-templates.md for page templates.
Rules:
- If page already exists → update it, append new information, don't overwrite existing content
- Keep the one-line definition stable unless the new content provides a clearly better one
- Prioritize updating "Sources" and "Related Pages" sections
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.
- 13d ago First seen · 107 lines · 79 tokens per session scan A 09e41fda18db
wiki-ingest is a skill published in the GitHub repository sanyuan0704/sanyuan-skills (3,906 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 867 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
obsidian
Obsidian vault: search/read/write notes, backlinks, Bases, Canvas.
loopx-doc-registry
Use when a connected LoopX project is asked to read, remember, record, index, register, or use a durable project material such as a Lark/wiki/design doc, research note, SOP, owner packet, migration report, benchmark paper, or external material source. Use even when the user does not mention LoopX or doc registry.
mindos-zh
A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.
excel-author
Create and edit Excel (.xlsx) workbooks with openpyxl. Supports formulas, charts, formatting, and data analysis.
ppt-author
Create and edit PowerPoint (.pptx) presentations programmatically. Requires python-pptx.
ocr-document
Extract text from PDFs, images, and scanned documents. Uses pymupdf (local) or optional cloud OCR APIs.