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.
npx skills add megaphone-tokyo/kioku --skill wiki-ingestgit clone --depth 1 https://github.com/megaphone-tokyo/kiokuWrote 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.
[](https://agentmods.dev/skills/megaphone-tokyo/kioku/wiki-ingest)<a href="https://agentmods.dev/skills/megaphone-tokyo/kioku/wiki-ingest"><img src="https://agentmods.dev/badge/skills/megaphone-tokyo/kioku/wiki-ingest/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.
<a href="https://agentmods.dev/skills/megaphone-tokyo/kioku/wiki-ingest"><img src="https://agentmods.dev/badge/skills/megaphone-tokyo/kioku/wiki-ingest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00106 | $0.02061 |
| Opus 5 | $0.00053 | $0.01030 |
| Sonnet 5 | $0.00021 | $0.00412 |
| Haiku 4.5 | $0.00011 | $0.00206 |
Grade A, and why
wiki-ingest 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-ingest
特定ファイル or 最近の git 変更から知見を抽出して claude-brain Wiki に取り込むスキル。/wiki-ingest-all の軽量版で、日常的に気になる点だけ Wiki に落とすために使う。
いつ使うか
- 特定のファイル/ディレクトリの知見だけ Wiki に追加したい時
- 最近の git 差分から設計判断やバグ修正の知見を拾いたい時
/wiki-ingest-allほど大掛かりにする必要がない時
プロジェクト全体を backfill したい場合は /wiki-ingest-all を使うこと。
前提
$OBSIDIAN_VAULTが設定され、$OBSIDIAN_VAULT/wiki/が存在すること- 引数なしモードは git リポジトリ内で実行すること
モード判定
モード A: パス指定 (/wiki-ingest <path>)
引数に 1 つ以上のパス (ファイル or ディレクトリ) が渡されたらこのモード。
# 例
/wiki-ingest src/auth/strategy.ts
/wiki-ingest docs/architecture/
/wiki-ingest src/middleware/ src/utils/errors.ts
モード B: git 差分 (/wiki-ingest 引数なし)
引数が空ならこのモード。最近の git 変更から Claude が判断して知見を抽出する。
ワークフロー
Step 0: 環境確認
/wiki-ingest-all の Step 0 と同じ:
test -n "$OBSIDIAN_VAULT" || echo "ERROR: OBSIDIAN_VAULT not set"
test -d "$OBSIDIAN_VAULT/wiki" || echo "ERROR: wiki/ missing"
PROJECT_NAME=$(git config --get remote.origin.url 2>/dev/null | sed -E 's#.*/([^/]+)(\.git)?$#\1#' | sed 's/\.git$//')
test -n "$PROJECT_NAME" || PROJECT_NAME=$(basename "$(pwd)")
Step 1: 対象の決定
モード A (パス指定)
- 指定されたパスが存在するか
test -eで確認 - ファイルなら直接読む (Read)
- ディレクトリなら
lsで中身を確認し、主要なもの (README, index.*, 設計ドキュメント等) を優先して読む - バイナリ/大きすぎるファイルはスキップ
モード B (git 差分)
最近のコミットをまず眺めて範囲を決める:
git log --oneline -10
git status
上の結果を見て Claude が範囲を判断する。固定の HEAD~N は使わない。典型的には:
- 直近 1〜3 コミットに明確なテーマがある → その範囲
- コミットが細かくバラバラ → 直近 1 コミットだけ
- 作業途中 (uncommitted) →
git diff+git diff --cachedのみ
決めた範囲で差分を取得:
git diff HEAD~<N>..HEAD --stat # まず概要
git diff HEAD~<N>..HEAD # 次に本体 (大きければファイル単位で絞る)
スキップする変更:
- lint / format / typo 修正
- 依存関係の単純なバージョンバンプ
- ファイル移動・リネームだけのコミット
- 生成物 (dist/, build/, lock ファイル)
Step 2: 既存 Wiki 監査
/wiki-ingest-all の Step 0-3 と同じ:
ls "$OBSIDIAN_VAULT/wiki/projects/"
ls "$OBSIDIAN_VAULT/wiki/concepts/"
ls "$OBSIDIAN_VAULT/wiki/patterns/"
cat "$OBSIDIAN_VAULT/wiki/index.md"
qmd MCP が利用可能ならキーワードで事前検索 (オプショナル)。
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.
- 11d ago First seen · 187 lines · 106 tokens per session scan A 4b8dba9e01ad
wiki-ingest is a skill published in the GitHub repository megaphone-tokyo/kioku (5 stars, last pushed 2mo ago), licensed MIT. It adds 106 tokens to every session and 2,061 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.
Other skills, from other repositories
setup
Set up or update TDD Guard for the current project. Detects the test framework, installs or updates the matching reporter, and configures or migrates its configuration to match the current specification.
hook-authoring
Guide creating Claude Code hooks with security-first design. Use for validation and enforcement.
agent-harness-optimizer
Use when agent harness optimization patterns for token efficiency, memory persistence, session management, and cross-harness parity. Use when optimizing agent performance, reducing token costs,.
usage-guard
Arm proactive 5-hour usage protection for long Claude Code sessions (batch, subagents, high window % at start). Daemon reads account-level 5-hour window usage (not per-session). User types /usage-guard at session start. Re-arm every sitting. If user mentions usage-guard by name, read this file and run arm.sh.
video-editor-full
A video post-production workflow that transcribes footage, removes silent sections, edits clips, adds effects and subtitles, and creates animated sections.
anything-to-md
Universal document to Markdown converter. Convert any file (PDF, Word, Excel, PPT, images, audio, video, YouTube URLs) to clean LLM-ready Markdown. Use when: User wants to convert documents to Markdown User needs to process entire directories of files User has YouTube videos or audio files to transcribe User wants to…