query

query is a command for Claude Code from briannaworkman/commonplace. It costs 12 tokens per session (305 once invoked), scanned A, original, MIT.

A wiki question-answering command that follows links between articles, answers only from the articles it reads, and saves the result in an output file.

In plain words
What is it for?
It is for answering questions from a local wiki and recording the question, answer, source path, and citations.
Why use it?
It makes the answer’s sources and reading path visible, while clearly marking gaps in the wiki.

Command for Claude Code

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 commands/briannaworkman/commonplace/query
Clone the repo
git clone --depth 1 https://github.com/briannaworkman/commonplace

Made for: Claude Code.

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 query

README.md
[![agentmods](https://agentmods.dev/badge/commands/briannaworkman/commonplace/query.svg)](https://agentmods.dev/commands/briannaworkman/commonplace/query)
Your own site
<a href="https://agentmods.dev/commands/briannaworkman/commonplace/query"><img src="https://agentmods.dev/badge/commands/briannaworkman/commonplace/query.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 305 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.

ModelPer sessionOnce invoked
Fable 5 $0.00012 $0.00305
Opus 5 $0.00006 $0.00152
Sonnet 5 $0.00002 $0.00061
Haiku 4.5 $0.00001 $0.00030

Measured 4d ago against content hash f29e995f89ea, 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 4d 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.

finished/.claude/commands/query.md · 40 lines

What it actually says

Answer this question using only the knowledge base:

$ARGUMENTS

1. Walk the graph

Read wiki/INDEX.md and pick the articles that look relevant. Read them. Follow their [[wikilinks]] outward to neighbouring articles as the question requires — the answer often sits in an article the index summary didn't obviously point at.

Keep track of the order you read things in. That path is part of the output.

2. Answer only from what the wiki says

Ground every claim in an article you actually read.

If the wiki doesn't cover the question, say so plainly and name the source that would close the gap. If it covers the question only partly, answer the part it covers and mark the boundary. Never fill a gap from general knowledge without labelling it as outside the wiki — a system that admits what it doesn't know is the only kind you can trust when it says it does.

3. Save it

Write outputs/YYYY-MM-DD-<slug>.md containing:

  • the question
  • the answer
  • the path taken through the graph — which articles you read, in order
  • citations — the articles, and the raw/ sources underneath them

4. Report

Give the answer inline and link the saved file.

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. 4d ago First seen · 40 lines · 12 tokens per session scan A f29e995f89ea

Subscribe to this mod's changes

query is a command published in the GitHub repository briannaworkman/commonplace (5 stars, last pushed 23d ago), licensed MIT. It adds 12 tokens to every session and 305 once invoked, about $0.0001 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.