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
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.
git clone --depth 1 https://github.com/nvk/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/commands/nvk/llm-wiki/inventory)<a href="https://agentmods.dev/commands/nvk/llm-wiki/inventory"><img src="https://agentmods.dev/badge/commands/nvk/llm-wiki/inventory/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/commands/nvk/llm-wiki/inventory"><img src="https://agentmods.dev/badge/commands/nvk/llm-wiki/inventory.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 | $0.00034 | $0.02684 |
| Opus 5.5 | $0.00014 | $0.01074 |
| Sonnet 5.5 | $0.00007 | $0.00537 |
| Haiku 4.5 | $0.00003 | $0.00268 |
Grade A, and why
inventory 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 1mo 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your task
Resolve the wiki. Do NOT broadly search the filesystem — follow these steps:
- Read
$HOME/.config/llm-wiki/config.json. If it hashub_path, expand leading~only (not tildes incom~apple~CloudDocs) and prefer that path; useresolved_pathonly as a fallback cache when the expandedhub_pathis unavailable andresolved_pathis initialized. If config has onlyresolved_path, use it. If the configured path can be statted but readingwikis.jsonor listingtopics/fails withOperation not permitted, stop and ask the user to grant Full Disk Access/iCloud Drive access to the launcher; do not fall back to~/wikiorresolved_path. Do not write machine-specificresolved_pathinto shared configs. - If no config → read
$HOME/wiki/_index.md. If it exists → HUB =$HOME/wiki. If nothing found, ask the user where to create the wiki. - Wiki location (first match):
--local→.wiki/in CWD;--wiki <name>→HUB/wikis.jsonlookup with portable path resolution (<HUB>,~, absolute, or HUB-relative); if the registry path is stale, fall back toHUB/topics/<name>; CWD has.wiki/→ use it; else → HUB. - Read
<wiki>/_index.mdto verify. If missing → stop with "No wiki found. Run/wiki initfirst."
Archive rule: inventory commands operate on active topic wikis by default. If a
named target is archived, stop and ask the user to restore it or rerun with
--include-archived. When explicitly included, list/update records only inside
that archived topic path and label the result as archived. Do not let archived
inventory records from archived topics appear in default cross-wiki summaries.
After resolving the wiki, read the inventory reference at skills/wiki-manager/references/inventory.md, then run the requested subcommand.
Inventory records are durable tracking objects, not compiled articles and not raw sources. Use them for physical or digital items, Ideas, ingest candidates, important entities, corpora to watch, open questions, recurring tasks, or "things we want to keep inventory of." They live under inventory/ and can point at raw/wiki/output files without moving them. Route kind: idea through /wiki:idea so it receives research, shaping, and explicit Project-promotion behavior.
Be opinionated. Before writing or migrating records, tell the user whether inventory is the right layer:
- Good fit: durable state with priority/status/next action, a physical/digital item to own/use/compare, a source/corpus to evaluate later, an entity/watch item, a deliverable-oriented Idea to shape, or a follow-up that should survive the chat session.
- Too small: one-off source to ingest now, a factual question, or a note with no future action. Route to ingest, query, or raw notes instead.
- Too big: hundreds of row-like items, datasets, message archives, snapshots, or collections. Create one corpus inventory record plus a dataset manifest or collection ingest, not one inventory record per row.
- Out of scope: authoritative source text (
raw/), synthesized knowledge (wiki/), generated deliverables (output/), project goals (WHY.md), or secrets/private operational data.
For bigger pivots, show a sample table of 1-3 proposed records and the recommendation before asking to apply. Default to dry-run for migrations and bulk conversions.
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.
- 1mo ago First seen · 184 lines · 34 tokens per session scan A da9199a7b26d
inventory is a command published in the GitHub repository nvk/llm-wiki (1,422 stars, last pushed 15d ago), licensed MIT. It adds 34 tokens to every session and 2,684 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
flow-nexus-user-tools
User management, storage, and system utilities.
flow-nexus-auth
Flow Nexus authentication and user management.
gtd
Canonical GTD entry point for capture, clarification, organization, review, and engagement.
prune-learnings
Manual command to invoke the pruning script for cleaning up old learnings.
pull-learnings
Pulls shared organization patterns into local org-patterns.toon.
end-session
Wrap up the work session with read-only evidence gathering, owner-classified documentation handoffs, gated issue sync, Kano refinement, and git hygiene checks.