wiki-query

wiki-query is a skill for Claude Code from shimo4228/claude-harness. It costs 191 tokens per session (2,280 once invoked), scanned A, original, MIT.

A query tool for an Obsidian vault, which is a folder of linked Markdown notes, including a wiki of concepts and research notes. It combines information from several notes and includes links back to its sources.

In plain words
What is it for?
Use it to ask the wiki questions, combine related research, and file useful answers back into the concept wiki.
Why use it?
It helps answer questions across scattered notes without losing track of where the information came from.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md.

Good fit Use it to ask the wiki questions, combine related research, and file useful answers back into the concept wiki.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shimo4228/claude-harness/wiki-query
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.

Any agent
npx skills add shimo4228/claude-harness --skill wiki-query
Clone the repo
git clone --depth 1 https://github.com/shimo4228/claude-harness

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/skills/shimo4228/claude-harness/wiki-query.svg)](https://agentmods.dev/skills/shimo4228/claude-harness/wiki-query)
Your own site
<a href="https://agentmods.dev/skills/shimo4228/claude-harness/wiki-query"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/wiki-query.svg" alt="Measured on agentmods" height="20"></a>
Per session 191 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,280 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 $0.00191 $0.02280
Opus 5 $0.00096 $0.01140
Sonnet 5 $0.00038 $0.00456
Haiku 4.5 $0.00019 $0.00228

Measured 3d ago against content hash 36cf920bf21f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 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/wiki-query/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wiki-query — LLM wiki への出典付き問い合わせ

Obsidian Vault 内の LLM wiki に問い合わせ、出典 [[ ]] を明記した合成回答を返す。 複数ページを横断して合成した良回答は wiki に書き戻す(filing)。

パターンの出自: wiki の運用モデル(LLM がメンテする markdown wiki、人間は curation と問いに集中)と query 書き戻し("good answers can be filed back into the wiki as new pages")は Andrej Karpathy の「LLM Wiki」構想に由来する。この skill ファイル自体は shimo4228 の実装。

このファイルが query 手順の正本。vault の CLAUDE.md §8-query はここに defer する。

Vault パス(固定)

VAULT="$HOME/Library/Mobile Documents/iCloud~md~obsidian/Documents/Obsidian Vault"
  • 概念ページ: $VAULT/wiki/concept/<概念名>.md
  • インデックス: $VAULT/wiki/index.md
  • 構造グラフ: $VAULT/wiki/graph.jsonld(symlink → ~/MyAI_Lab/daily-research/graph.jsonld
  • 原資料: $VAULT/daily-research/, $VAULT/archive/

制約

  • source 層は不変: daily-research/ archive/ 99_Attachment/ には書き込まない。
  • 書き込み対象は wiki/concept/ + wiki/log.md + index 再生成のみ。source の新規取り込み(ingest)と wiki 全体の lint は vault セッション専用のまま。
  • Obsidian 起動中に vault の .md を書かない(iCloud 同期競合)。書き戻し手順 1 のチェックを必ず通す。
  • iCloud dataless プレースホルダに注意: 読んだファイルの本文が空なら未ダウンロードの可能性。その旨を報告する。

手順(query)

  1. $VAULT/wiki/index.md を Read し、問いに関連しそうな concept ページを特定する。
  2. 該当 concept ページを Read する(複数可)。必要なら「言及ソース」節が指す daily-research/ ノートまで遡って Read する。
  3. 構造的な問い(このクラスタに属する記事は?クラスタ間の関係は?)には wiki/graph.jsonld を、合成された理解には concept ページを使い、相互補完する。
  4. 出典([[ ]])を明記して合成回答する。claim ごとに、どの concept ページ / daily-research ノート由来かが追えること。
  5. wiki に該当が無ければ「未 ingest」と明言し、vault セッションで /ingest することを提案する(このセッションで ingest を代行しない)。
  6. 回答が下記の filing 基準を満たすなら、書き戻しを実行する。

書き戻し(query filing)

Filing 基準

filing するのは、複数の concept ページ / ソースを横断して新しく合成された比較・分析・概念間の接続だけ。

  • 単一ページの言い換え・要約 → filing しない(既にページがある)
  • wiki 外の知識だけで答えた回答 → filing しない(それは ingest の領域)
  • 迷ったら filing しない — wiki の信頼性 > 網羅性(原典: 不正確な回答を wiki に残さない)

形は 2 通り: 新規 concept ページ(合成が独立した概念単位になる場合)か、既存ページへの統合(既存概念の「主要な主張」「関連概念」「オープンクエスチョン」に足す場合)。

Filing 手順

  1. Obsidian チェック: pgrep -x Obsidian。起動中なら graceful 終了(osascript -e 'quit app "Obsidian"' → 数秒待って再確認)。終了できなければ filing を skip し、その旨と filing 候補の内容を報告する(回答自体は返してよい)。
  2. 名寄せ: wiki/index.md$VAULT/scripts/tag_consolidate.pyTAG_MERGE_MAP を確認し、新規ページか既存ページ統合かを決める。表記揺れ・英語名は新タグを作らず正規形 + aliases で吸収。
  3. 新規ページは下記骨格で wiki/concept/<正規概念名>.md に作成。ファイル名 = # 見出し = 正規タグを一致させる。関連概念に最低 2 リンクを張り、相手ページの「関連概念」節にも逆リンクを追記する(孤立ページを作らない)。
  4. 出典規律: wiki 由来の claim は [[ ]] リンク。研究 repo 由来の claim は repo 名 + ファイルパスを素のテキストで併記する(repo へは wikilink を張れないが provenance は残す)。
  5. log 追記: wiki/log.md## [YYYY-MM-DD] query-filing | <問い> → [[<concept>]] を 1 行追記。
  6. index 再生成 + 検証: cd "$VAULT" && /opt/homebrew/bin/python3 scripts/wiki_index.py --apply && /opt/homebrew/bin/python3 scripts/wiki_lint.py。lint がエラーを出したら自分の filing 分を修正する。

Read the full file on GitHub · 94 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. 3d ago Changed 36cf920bf21f
  2. 8d ago First seen · 94 lines · 191 tokens per session scan A e8b7ad85da14

Subscribe to this mod's changes

wiki-query is a skill published in the GitHub repository shimo4228/claude-harness (2 stars, last pushed 2d ago), licensed MIT. It adds 191 tokens to every session and 2,280 once invoked, about $0.0010 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.

Related

Other skills, from other repositories

onboard

One-time researcher onboarding interview that compiles a taste/ corpus (SOUL.md, STYLE.md, METHODOLOGY.md, DISMISSALS.md, MEMORY.md, INDEX.md) capturing the researcher's intellectual taste, beliefs, and values. Auto-injects INDEX.md into every future session via SessionStart. Triggers on first install ("no taste…

Rockielab/rockie-claude · 117 tokens

write-terva-lore

Author terva lore. Lore is context that a person authors in files. terva injects it only when it is keyword-relevant, or always-on. Use to create/add/write lore, "world info", a lorebook entry, keyed background, or a book of facts for a character.

terva-sh/terva · 66 tokens

scheduled-notes

Persistent notes a scheduled/recurring agent reads as its FIRST action and writes as its LAST action, so a weekly/nightly autonomous run "knows where it left off." Use inside /loop or /schedule tasks that span multiple wake-ups. Pairs with hypothesis calibration and the experiment queue.

Rockielab/rockie-claude · 63 tokens

agent-adoption-triage

Five-question triage for routing AI work to the right architecture — script, algorithmic search, LLM workflow, or autonomous agentic loop — before any agent is built. Use when someone says "let's build an agent for X", when deciding whether a use case actually needs an autonomous agent, when reviewing an agent…

shimo4228/agent-adoption-triage · 143 tokens

handoff

Compact the current session into a handoff document. A fresh session or another agent can pick it up with no need to re-derive context. Use when asked to hand off, hand over, wrap up for another session or agent, or park work mid-stream.

terva-sh/terva · 56 tokens

retrospective

Distill the reusable lessons of this session into the durable homes that shape future sessions. The lessons are corrections, conventions you discovered, and traps you hit. The homes are the project or global AGENTS.md, a project skill, and memory when available. Use when asked for a retro, to capture or remember…

terva-sh/terva · 76 tokens