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 agentmods add commands/nvk/llm-wiki/querygit clone --depth 1 https://github.com/nvk/llm-wikiWhat 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 | $0.00031 | $0.00759 |
| Opus 5 | $0.00015 | $0.00380 |
| Sonnet 5 | $0.00006 | $0.00152 |
| Haiku 4.5 | $0.00003 | $0.00076 |
Grade A, and why
query 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 yesterday.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read-Only Wiki Query
Read skills/wiki-manager/references/query-lite.md, then answer $ARGUMENTS
from the selected wiki. This command is always read-only: do not update indexes
or append to log.md.
Parse
- Everything that is not a flag is the question.
--quick: use index summaries only.- No depth flag: standard index-first query.
--deep: inspect all relevant compiled articles, links, and raw evidence.--raw: allow targeted raw-source reads; implied by--deep.--list: return ranked matching files instead of a synthesized answer.--include-archived: explicitly permit archived reads and label them.--resume: give a compact activity briefing before answering any question.--tagand--category: constrain candidate selection.--with <wiki>: use an active supplementary wiki as secondary context.--wiki <name>and--local: select the primary wiki.
Depth
Quick
Read the primary _index.md and only the relevant branch indexes. Answer from
their summaries and tags. If they are insufficient, say so and recommend the
standard mode. Cite the index paths used.
Standard
Use the query-lite protocol: master index, relevant branch index, then the minimum exact articles. Use one bounded Grep only when indexes miss a likely match. Follow directly relevant See Also links. Cite exact files and surface confidence or evidence gaps that affect the answer.
Deep
Read all relevant branch indexes and articles, follow relevant cross-links,
search wiki/ and raw/ with bounded patterns, and inspect active sibling
indexes for overlap. Archived sibling indexes may be reported separately, but
archived article bodies require --include-archived.
List Mode
Return a compact ranked list. Rank title matches above summary matches, summary
above body matches, and multiple-term matches above single-term matches. Show
title, exact path, summary, and tags. Include raw matches only with --raw.
Keep archived results separate and only include them when explicitly allowed.
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.
- yesterday First seen · 77 lines · 31 tokens per session scan A 05b7e052397e
query is a command published in the GitHub repository nvk/llm-wiki (1,163 stars, last pushed 4d ago), licensed MIT. It adds 31 tokens to every session and 759 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 2026-08-30.
Other commands, from other repositories
implement
Execute phased implementation with validation gates.
workflow-claude-commands
Track Claude Code commands report changes and find what needs updating.
weather-orchestrator
Fetch Dubai weather and create an SVG weather card.
project
Generate project documentation (product.md, structure.md, tech.md, codemaps/).
review
Code review with security and @MX tag compliance check.
research-verify
Verify existing research findings against independent primary sources. Upgrades confidence from 'sources agree' to 'independently verified.'.