llm-wiki-newsroom: Command for Claude Code

.claude/commands/wiki-query.md

wiki-query is a command for Claude Code from alfadur7/llm-wiki-newsroom. It costs 0 tokens per session (1,670 once invoked), scanned A, original, MIT.

A command for asking questions about an LLM Wiki, a collection of linked information about large language models, and getting a synthesized answer.

In plain words
What is it for?
Use it to answer questions about entities, relationships, topics, facts, overall themes, or disagreements in the wiki. It can also save a synthesized result when requested.
Why use it?
It gives a defined way to search across the wiki and combine information instead of reading sources one by one.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is alfadur7/llm-wiki-newsroom's own configuration. It tells Claude Code how to work on llm-wiki-newsroom itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything llm-wiki-newsroom configures →

Reuse

Borrowing it

Nothing to install: this file belongs to alfadur7/llm-wiki-newsroom. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/alfadur7/llm-wiki-newsroom/main/.claude/commands/wiki-query.md
Clone the repo
git clone --depth 1 https://github.com/alfadur7/llm-wiki-newsroom

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 wiki-query

README.md
[![agentmods](https://agentmods.dev/badge/commands/alfadur7/llm-wiki-newsroom/wiki-query/github.svg)](https://agentmods.dev/commands/alfadur7/llm-wiki-newsroom/wiki-query)
Your own site
<a href="https://agentmods.dev/commands/alfadur7/llm-wiki-newsroom/wiki-query"><img src="https://agentmods.dev/badge/commands/alfadur7/llm-wiki-newsroom/wiki-query/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.

agentmods 80×15 button for wiki-query

Your own site · 80×15
<a href="https://agentmods.dev/commands/alfadur7/llm-wiki-newsroom/wiki-query"><img src="https://agentmods.dev/badge/commands/alfadur7/llm-wiki-newsroom/wiki-query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,670 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01670
Opus 5 $0.00000 $0.00835
Sonnet 5 $0.00000 $0.00334
Haiku 4.5 $0.00000 $0.00167

Measured 12d ago against content hash 4d34c66eb109, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

wiki-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 12d 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.

.claude/commands/wiki-query.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Query the LLM Wiki and synthesize an answer.

Usage: /wiki-query <question> — required argument

If $ARGUMENTS is empty: print the usage below and stop.

Usage: /wiki-query <question>

Examples:
  /wiki-query OpenSourceInitiative open source AI definition
  /wiki-query What are the main themes across all sources?
  /wiki-query summarize the open weights vs open source debate

Traversal Pattern

Classify the question as one of 6 types (Entity-centric / Relation / Topic / Fact / Meta / Contradiction), then branch.

Mode Cycle Owner
Simple answer (no save) Reading Reporter (mode=ground) — broad wiki read + tools/query.py graph + answer synthesis
Synthesis save L2-3 synthesis cycle Columnist GROUND·APPLY → Copy Editor → Desk → Editor-in-Chief gate

The rule for question-type classification → mode branch is the sole responsibility of the ## Mode Routing section below.

Question Type Classification (6 Types)

Read the question and classify it as 1 of 6 types, then enter the relevant procedure. When ambiguous, default to Topic.

Type Trigger Recommended --edge-type Entry tool
Contradiction "Contradiction between A and B?", "What's at issue?" contradicts tools/query.py graph neighbors X --edge-type contradicts
Entity-centric "What does X cite·oppose?" cites,contradicts tools/query.py graph neighbors X
Topic "Overview of field X", "Definition of X" defines,cites mcp__qmd__query (structured: intent+vec/lex)
Fact "Did X announce Y?" cites mcp__qmd__query (lex-centered)
Relation "Relationship between A and B?" (full default) tools/query.py graph path A B
Meta "Wiki structure", "Hub distribution" (full default) read root meta pages

Additional natural-language intent mapping (when the user does not state one of the 6 types):

  • "where opinions diverge" · "controversy" → --edge-type contradicts
  • "primary source" · "announcement·citation" → --edge-type cites
  • "defined concept" → --edge-type defines
  • "simple mention" → --edge-type references
  • "appearing together" · "co-occurring" → --edge-type inferred

Read the full file on GitHub · 103 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.

  1. 12d ago First seen · 103 lines · 0 tokens per session scan A 4d34c66eb109

Subscribe to this mod's changes

wiki-query is a command published in the GitHub repository alfadur7/llm-wiki-newsroom (85 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,670 tokens. 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.