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 TrueHOOHA/LLM-Wiki --skill llm-wiki-ingestgit clone --depth 1 https://github.com/TrueHOOHA/LLM-WikiWrote 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/truehooha/llm-wiki/llm-wiki-ingest)<a href="https://agentmods.dev/skills/truehooha/llm-wiki/llm-wiki-ingest"><img src="https://agentmods.dev/badge/skills/truehooha/llm-wiki/llm-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/truehooha/llm-wiki/llm-wiki-ingest"><img src="https://agentmods.dev/badge/skills/truehooha/llm-wiki/llm-wiki-ingest.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 | $0.00072 | $0.01374 |
| Opus 5 | $0.00036 | $0.00687 |
| Sonnet 5 | $0.00014 | $0.00275 |
| Haiku 4.5 | $0.00007 | $0.00137 |
Grade A, and why
llm-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 10d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki Ingest Skill
Purpose
Integrate a newly provided raw source into the wiki while preserving raw-source immutability and maintaining index/log bookkeeping. The wiki is an OKF v0.1 bundle (see SPEC.md); wiki/ is the bundle root.
Preconditions (must pass before edits)
- The operator explicitly requested ingestion.
- The source file exists at
raw/sources/<file>orraw/assets/<file>. - The workflow will not modify anything under
raw/.
Guardrails
- Immutable raw files: Never edit, rename, move, or delete any file under
raw/. - Wiki ownership: Create/update pages only under
wiki/(unless operator explicitly overrides). - Append-only log: Only append a new date-grouped entry to
wiki/log.md; never rewrite or reorder prior entries. - Index freshness: Any wiki page change in this workflow requires
wiki/index.mdto be rebuilt before completion. - OKF conformance: Created/updated pages must satisfy OKF §9 (parseable frontmatter with non-empty
type) and the producer conventions inAGENTS.md§ Page Types & Conventions. - Obsidian wikilinks: Internal note-to-note links use Obsidian wikilinks (
[[note]]/[[note|Display]]), resolving by file basename or frontmatteraliases. Standard markdown links are used ONLY for external URLs (https://…). SeeAGENTS.md§ Cross-linking. - Single source of truth: The schema is defined in
AGENTS.md. This skill enforces it; it never re-defines page types, frontmatter, or sections inline.
Required Step Order (exact)
- Read the raw source from
raw/sources/orraw/assets/.- If text references images/assets, read those after the main text.
- Discuss key takeaways with operator before framing final extraction.
- Minimal prompt:
- "I summarized the source. What should I emphasize?"
- "Any specific connections to existing entities/concepts you want prioritized?"
- "What should be de-emphasized or deferred?"
- Minimal prompt:
- Write source summary page in
wiki/sources/using filenameYYYY-MM-DD--source-title-slug.md, followingAGENTS.md§ Source Pages. Set frontmatterresourceto the raw source path (e.g.raw/sources/file.pdf); settitle,description,tags,created,timestamp(today). - Update/create entity pages in
wiki/entities/for concrete things mentioned, followingAGENTS.md§ Entity Pages. Use Obsidian wikilinks ([[note]]or[[note|Display]]) for cross-links and# Citationsentries — the link target is the note's basename or one of itsaliases. When updating an existing entity page from this source, increment itssource_countby 1 and bumptimestampto today; when creating a new page, setsource_count: 1. - Update/create concept pages in
wiki/concepts/for abstract ideas mentioned, followingAGENTS.md§ Concept Pages, applying the samesource_countincrement andtimestampbump rule as step 4. - Rebuild
wiki/index.mdfollowing the Canonical rebuild procedure inAGENTS.md§ Update Rules for Special Files (wiki/index.md): scan every.mdunderwiki/entities/,wiki/concepts/,wiki/sources/, andwiki/syntheses/(neverwiki/templates/), read each page's frontmatter, and rewrite the five sections (Entities, Concepts, Sources, Syntheses, Statistics) as bullet lists (* [[note-name|Title]] - description), preserving theokf_version: "0.1"frontmatter. The index must list exactly the pages that exist on disk. - Append to
wiki/log.mda single new date-grouped entry — newest first, never edit or reorder prior entries (OKF §7).- Heading:
## YYYY-MM-DD - Bullets:
* **Ingest**: <Source Title> — <one-line summary of what was created/updated>.,* **Pages touched**: <list>.,* **Notes**: ...,* **Open questions**: ...
- Heading:
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.
- 10d ago First seen · 56 lines · 72 tokens per session scan A 3f966b2742a9
llm-wiki-ingest is a skill published in the GitHub repository TrueHOOHA/LLM-Wiki (22 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,374 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
data-report
A report generator that turns CSV, Excel, or JSON data into a complete HTML page with key figures, charts, written insights, and a data table.
doc-convert
A converter that formats Markdown documents as HTML, printable PDF files, or long PNG images. Markdown is plain text with simple formatting marks for headings, lists, tables, and code.
knowledge_base
Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.
exam-study-guide
A study-guide builder for a completed exam chapter that has not yet passed its required checks. It creates a structured teaching checklist and, in full mode, a self-contained HTML and printable PDF guide with readable formulas, visible images, explanations, examples, and answers.
dashi-ppt
A skill for creating presentation slides as offline HTML pages that can be edited in a browser. It uses ready-made visual themes and can export the result as PPTX or PDF files.
ppt-generation
Generate PPTX presentations from slide plan + content.