LLM Wiki is a system that uses AI agents to research sources, compile knowledge bases, organize project briefs, and answer questions from the resulting wiki. It is used to turn rough ideas and investigations into structured, reusable knowledge for agents, including Claude Code, Codex, and OpenCode. The catalogue entries are commands, hooks, skills, instructions, and a plugin that implement its workflow.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add nvk/llm-wiki/plugin install claude-pluginWrote 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/nvk/llm-wiki/wiki-manager)<a href="https://agentmods.dev/skills/nvk/llm-wiki/wiki-manager"><img src="https://agentmods.dev/badge/skills/nvk/llm-wiki/wiki-manager.svg" alt="Measured on agentmods" 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 | $0.00141 | $0.06102 |
| Opus 5 | $0.00071 | $0.03051 |
| Sonnet 5 | $0.00028 | $0.01220 |
| Haiku 4.5 | $0.00014 | $0.00610 |
Grade A, and why
wiki-manager scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
IPv4 retry (`curl -4`) when media hosts hang on IPv6. Do not pretend that "all" How it starts
The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Wiki Manager
You manage an LLM-compiled knowledge base. Source documents are ingested into raw/, then incrementally compiled into a wiki of interconnected markdown articles. Claude Code is both the compiler and the query engine — no Obsidian, no external tools.
Hub Path
Resolution: At the start of every operation, resolve HUB by reading ~/.config/llm-wiki/config.json first. Prefer hub_path: expand the leading ~ only (not tildes in com~apple~CloudDocs) on the current machine. Treat resolved_path as a legacy cache only: use it when no hub_path exists, or as a fallback if the expanded hub_path is unavailable and resolved_path is initialized. Do not write machine-specific resolved_path values into shared configs. If no config file exists, try ~/wiki/_index.md as a fallback. If stat/existence checks succeed but reading wikis.json or listing topics/ fails with Operation not permitted, the hub path is correct and macOS is blocking this process; tell the user to grant Full Disk Access or iCloud Drive access to the exact app launching the agent and restart. Do not switch to ~/wiki or resolved_path for that error. See references/hub-resolution.md for the full protocol.
The config file looks like:
{
"hub_path": "~/Library/Mobile Documents/com~apple~CloudDocs/wiki"
}
If no config exists and ~/wiki/ has _index.md, that works too. But config is checked first — in sandboxed environments ~/wiki/ may not be accessible. All references to ~/wiki/ below mean HUB.
Wiki Location
Topic sub-wikis are the default. HUB is a hub — content lives in HUB/topics/<name>/. Each topic gets isolated indexes, sources, and articles. This keeps queries focused and prevents unrelated topics from polluting each other's search space.
For collection families that will grow across subjects, prefer kind-first topic
slugs such as memes-bitcoin, memes-ethereum, tools-bitcoin, or
examples-seedqr. Use subject-first slugs when the subject is the primary
research area and the collection is only one artifact within that topic.
What ships with it
22 files 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.
- references/adapters.md 13 KB
- references/archive.md 6.6 KB
- references/audit.md 7.9 KB
- references/checkpoints.md 6.4 KB
- references/command-prelude.md 6.9 KB
- references/compilation.md 9.5 KB
- references/datasets.md 9.8 KB
- references/feedback.md 3.6 KB
- references/hub-resolution.md 6.8 KB
- references/ideas.md 4.4 KB
- references/indexing.md 5.2 KB
- references/ingestion.md 17 KB
- references/inventory.md 15 KB
- references/librarian.md 14 KB
- references/linting.md 42 KB
- references/portfolio.md 2.9 KB
- references/projects.md 9.2 KB
- references/query-lite.md 2.6 KB
- references/research-infrastructure.md 22 KB
- references/sessions.md 9.1 KB
- references/specialists.md 6.6 KB
- references/wiki-structure.md 24 KB
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.
- 6d ago First seen · 404 lines · 141 tokens per session scan A 5891b3028ef1
wiki-manager is a skill published in the GitHub repository nvk/llm-wiki (1,193 stars, last pushed 9d ago), licensed MIT. It adds 141 tokens to every session and 6,102 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
co-mail-and-drive
Read and send mail from the user's own Gmail or Outlook account, send from the agent's own address, manage their Outlook contacts, and list/search/download/upload their Google Drive files — with co gmail, co outlook, co email, and co gdrive. Use when the user asks about their inbox, an email they received or want to…
moai-docs-generation
Documentation generation patterns for technical specs, API docs, user guides, and knowledge bases using real tools like Sphinx, MkDocs, TypeDoc, and Nextra. Use when creating docs from code, building doc sites, or automating documentation workflows.
nw-diagram
Generates C4 architecture diagrams (context, container, component) in Mermaid or PlantUML. Use when creating or updating architecture visualizations.
moai-domain-html-report
Markdown-to-single-file-HTML report renderer. Six modes (status, incident, plan, explainer, financial, pr) selected by report type, crossed with three audience tiers (expert, basic, learn) derived from the active output style. The basic and learn tiers enrich the HTML with mermaid flowcharts, worked examples, and…
docx
Read, create, and convert Microsoft Word (.docx) documents — extract text and tables, build reports from markdown/JSON, and export to PDF.
xlsx
Read, create, and convert Microsoft Excel (.xlsx) and CSV spreadsheets — extract sheets and tables to JSON, build workbooks from JSON/CSV, and export to PDF.