A question-and-search workflow for a markdown wiki. It either lists relevant pages for keywords or writes a cited answer by combining information from the wiki.

Looking up topics, locating pages, explaining wiki content, summarizing information, and answering questions with references to the source pages.

It helps users find the right documentation and understand it without manually opening and comparing pages.

query — Skill for Claude Code and Codex by tom5610: A question-and-search workflow for a markdown wiki.

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.

agentmods

npx agentmods add skills/tom5610/llm-wiki/query

Any agent

npx skills add tom5610/llm-wiki --skill query

Clone the repo

git clone --depth 1 https://github.com/tom5610/llm-wiki

Made for: Claude Code, Codex.

Or install llm-wiki, the plugin that ships this one along with the rest of its 5 skills, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tom5610/llm-wiki/query.svg)](https://agentmods.dev/skills/tom5610/llm-wiki/query)

Your own site

<a href="https://agentmods.dev/skills/tom5610/llm-wiki/query"><img src="https://agentmods.dev/badge/skills/tom5610/llm-wiki/query.svg" alt="Measured on agentmods" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,715 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00091	$0.01715
Opus 5	$0.00046	$0.00857
Sonnet 5	$0.00018	$0.00343
Haiku 4.5	$0.00009	$0.00171

Measured 3d ago against content hash cc739705a823, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

skills/query/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Query workflow

The user asks a question. Use $ARGUMENTS as the question if provided (e.g., /query How do the main concepts in the wiki relate to each other?).

Prerequisites

Verify wiki/index.md exists. If missing, suggest running /ingest on a source first — it will bootstrap the wiki automatically.

Detect mode. Determine whether the user wants navigation or understanding:
- Navigational — the input is keywords, a lookup, or asks "where is X?" / "which pages mention X?" / "find X". The user wants a results list, not a composed answer.
- Synthesis — the input is a natural language question, asks for explanation, comparison, or summary. The user wants an answer.
Mode override: If the user explicitly says "just search" or "just list pages", use navigational mode regardless of input structure. If the user says "explain" or "synthesize", use synthesis mode. When in doubt, default to synthesis — it's strictly more useful than a list of links.
Find relevant pages.
- Read wiki/index.md to identify candidate pages.
- Lens filtering (optional): If the user's question specifies a domain or explicitly requests results from a particular lens (e.g., "in the ML lens" or "within compliance"), filter candidates to pages with the matching lens frontmatter field. If no lens is specified, search across all pages (default).
- If the index is insufficient, use a tiered search:
  - Tier 1 — Filenames: Scan filenames in wiki/ for query term matches.
  - Tier 2 — Headings and frontmatter: Grep for the query in page titles, headings (#), and frontmatter tags/title fields.
  - Tier 3 — Body text: Grep the full body text of remaining pages.
  - For wikis with >50 pages, stop after Tier 2 if 5+ matches are found.
Respond according to mode.

If navigational: Present a concise results list. For each matching page, show:
- Page title as a [[wikilink]]
- Page type and tags
- Most relevant excerpt (1-3 lines of context)
- If no results: suggest related terms, alternative spellings, or rephrasing as a synthesis question.
- Do not read full pages or synthesize — keep it cheap and fast.

Read the full file on GitHub · 83 lines

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.

3d ago First seen · 83 lines · 91 tokens per session scan A cc739705a823

Subscribe to this mod's changes

query is a skill published in the GitHub repository tom5610/llm-wiki (2 stars, last pushed 4mo ago), licensed MIT. It adds 91 tokens to every session and 1,715 once invoked, about $0.0005 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.

Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens