llm-wiki-builder

llm-wiki-builder is a skill for Claude Code, Codex from u9401066/asset-aware-mcp. It costs 38 tokens per session (316 once invoked), scanned A, original, Apache-2.0.

A skill that builds or refreshes Foam-compatible wikis from documents and notes. Foam is a Markdown-based knowledge system that connects notes with links, while an LLM wiki organises source material for language-model retrieval.

In plain words
What is it for?
Use it to create, update, repair, or extend evidence-based Markdown wikis with source links and provenance.
Why use it?
It keeps research notes connected to their source documents, citations, tables, and figures instead of losing where claims came from.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create, update, repair, or extend evidence-based Markdown wikis with source links and provenance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/u9401066/asset-aware-mcp/llm-wiki-builder
Install

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.

Any agent
npx skills add u9401066/asset-aware-mcp --skill llm-wiki-builder
Clone the repo
git clone --depth 1 https://github.com/u9401066/asset-aware-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for llm-wiki-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/u9401066/asset-aware-mcp/llm-wiki-builder/github.svg)](https://agentmods.dev/skills/u9401066/asset-aware-mcp/llm-wiki-builder)
Your own site
<a href="https://agentmods.dev/skills/u9401066/asset-aware-mcp/llm-wiki-builder"><img src="https://agentmods.dev/badge/skills/u9401066/asset-aware-mcp/llm-wiki-builder/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.

agentmods 80×15 button for llm-wiki-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/u9401066/asset-aware-mcp/llm-wiki-builder"><img src="https://agentmods.dev/badge/skills/u9401066/asset-aware-mcp/llm-wiki-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 316 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00316
Opus 5 $0.00019 $0.00158
Sonnet 5 $0.00008 $0.00063
Haiku 4.5 $0.00004 $0.00032

Measured 11d ago against content hash e84ba0fba609, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

llm-wiki-builder 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 11d 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.

.cline/skills/llm-wiki-builder/SKILL.md · 36 lines

What it actually says

LLM Wiki Builder

Use this skill when the user asks to create, refresh, repair, or extend a Foam wiki or LLM-readable document evidence wiki.

Read First

  • .clinerules/35-foam-llm-wiki.md
  • .clinerules/workflows/llm-wiki-build.md

Multi-Tool Choreography

  1. Inspect the filesystem for the wiki root, Foam markers, existing note style, and link conventions.
  2. Use Asset-Aware document tools to inspect ingested PDFs, DOCX/DFM sessions, tables, figures, sections, and citation-ready spans.
  3. Use citation bundles, evidence health checks, and optional knowledge exports when claims need source-backed summaries.
  4. Write or update Markdown notes with Foam-compatible wikilinks and preserved AssetRef, document, table, figure, section, DOI, URL, or local-file source identifiers when available.
  5. Validate generated links and report unresolved wiki TODOs separately from completed notes.

Output Contract

  • Keep the note graph readable in Foam and useful for LLM retrieval.
  • Preserve source provenance close to claims.
  • Ask before bulk rewrites, destructive cleanup, or overwriting curated notes.
  • Do not leave broken wikilinks hidden in generated files.
Changes

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.

  1. 11d ago First seen · 36 lines · 38 tokens per session scan A e84ba0fba609

Subscribe to this mod's changes

llm-wiki-builder is a skill published in the GitHub repository u9401066/asset-aware-mcp (0 stars, last pushed 23d ago), licensed Apache-2.0. It adds 38 tokens to every session and 316 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

redlines

Use when you need to generate tracked changes in Word documents from diff output, apply redlines from AI agents to DOCX files, or convert text diffs into native Word revisions.

LegalQuants/lq-skills · 39 tokens

office-word-diff

Use when you need to apply word-level tracked changes to Microsoft Word documents programmatically, preserve formatting through diffs, or integrate with Office.js for document transformation.

LegalQuants/lq-skills · 37 tokens

superdoc-redlines

Use when you need to apply tracked changes and comments to DOCX files programmatically, merge multi-agent edits with conflict resolution, or produce native Word revisions from AI agent output.

LegalQuants/lq-skills · 40 tokens

corpus-knowledge-engineering

Turn document corpora (books, merged TXT, PDF/EPUB, OCR text) into structured agent knowledge: normalize → deterministic source segmentation → chapter maps with provenance → book skills → evaluation gates. Use when the user wants to convert books/materials into AI skills, build a knowledge base from a corpus, evaluate…

gootf/corpus-knowledge-engineering · 89 tokens

deckprobe

Inspect PDF, Microsoft Office (docx/xlsx/pptx and legacy doc/xls/ppt), and Apple iWork (key/numbers/pages) files without opening or rendering them. Use for page and slide and sheet counts, title/author/created metadata, encryption and macro and digital-signature and JavaScript risk signals, sheet and table structure…

deckflow/deckprobe · 130 tokens

法律文件脱敏处理

A browser-based and Python tool for removing sensitive details from legal Word documents and restoring them later. It can replace information such as names, dates, prices, bank accounts and case numbers while preserving document formatting.

moyupeng0422/legal-doc-redactor · 128 tokens