wiki-query

A workflow for answering questions from a team wiki, a collection of internal documentation pages. It searches relevant pages, combines their contents into an answer, and cites the source of each factual claim.

In plain words
What is it for?
Finding internal documentation and producing cited answers from it, with an optional saved answer file.
Why use it?
It reduces unsupported answers by keeping responses tied to the information documented in the wiki and clearly showing gaps.

Skill for Claude CodeCodex

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/darkcodepe/brainstem/wiki-query
Any agent
npx skills add DarkCodePE/brainstem --skill wiki-query
Clone the repo
git clone --depth 1 https://github.com/DarkCodePE/brainstem

Made for: Claude Code, Codex.

Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 381 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 $0.00010 $0.00381
Opus 5 $0.00005 $0.00191
Sonnet 5 $0.00002 $0.00076
Haiku 4.5 $0.00001 $0.00038

Measured yesterday against content hash fae4cccec8de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

src/wiki_agent/skills/wiki-query/SKILL.md · 57 lines

What it actually says

wiki-query

Search the wiki and synthesise a grounded answer with citations.

Steps

  1. Search wiki/index.md for relevant pages matching the question
  2. Read the top matching pages (up to max_pages)
  3. Synthesise an answer grounded in wiki content
  4. Cite every factual claim with (source: wiki/path/to/page.md)
  5. Optionally file the answer at wiki/answers/<slug>.md

Error handling

  • If no relevant pages found, return NO_RELEVANT_PAGES error
  • Never hallucinate information not present in the wiki
  • Clearly state gaps when wiki coverage is partial
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. yesterday First seen · 57 lines · 10 tokens per session scan A fae4cccec8de

Subscribe to this mod's changes

wiki-query is a skill published in the GitHub repository DarkCodePE/brainstem (1 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 381 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.