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-ingest-allgit 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-all)<a href="https://agentmods.dev/skills/megaphone-tokyo/kioku/wiki-ingest-all"><img src="https://agentmods.dev/badge/skills/megaphone-tokyo/kioku/wiki-ingest-all/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-all"><img src="https://agentmods.dev/badge/skills/megaphone-tokyo/kioku/wiki-ingest-all.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 | $0.00140 | $0.03777 |
| Opus 5 | $0.00070 | $0.01888 |
| Sonnet 5 | $0.00028 | $0.00755 |
| Haiku 4.5 | $0.00014 | $0.00378 |
Grade A, and why
wiki-ingest-all scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-ingest-all
現在の作業ディレクトリ ($(pwd)) にあるプロジェクトを網羅的に読み取り、claude-brain Wiki ($OBSIDIAN_VAULT/wiki/) に知見を書き込むスキル。
いつ使うか
- 既存プロジェクトの知見を 初めて Wiki に取り込む時 (backfill)
- プロジェクトの全体像を 1 回で Wiki に記録したい時
- 新しいプロジェクトを始めて、最初に構造を Wiki に固定したい時
同じプロジェクトに対して 2 回目以降の実行は 更新モード として扱い、既存ページを置き換えずに追記・補強する。
前提
$OBSIDIAN_VAULTが設定され、$OBSIDIAN_VAULT/wiki/が存在すること- 現在のカレントディレクトリが対象プロジェクトのルートであること
- 初回実行なら、Wiki は空か最小限の状態を想定 (qmd/重複チェックはその前提で動く)
ワークフロー
Step 0: 環境確認と既存 Wiki 監査
最初に以下を全て実行する。1 つでも欠けたらユーザーに指示を仰いで中断。
# 0-1. Vault 確認
test -n "$OBSIDIAN_VAULT" || echo "ERROR: OBSIDIAN_VAULT not set"
test -d "$OBSIDIAN_VAULT/wiki" || echo "ERROR: wiki/ missing; run setup-vault.sh first"
# 0-2. プロジェクト名の決定
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)")
echo "Project: $PROJECT_NAME"
# 0-3. 既存 Wiki の監査 (重複回避のため)
ls "$OBSIDIAN_VAULT/wiki/projects/" 2>/dev/null
ls "$OBSIDIAN_VAULT/wiki/concepts/" 2>/dev/null
ls "$OBSIDIAN_VAULT/wiki/patterns/" 2>/dev/null
ls "$OBSIDIAN_VAULT/wiki/decisions/" 2>/dev/null
ls "$OBSIDIAN_VAULT/wiki/analyses/" 2>/dev/null
cat "$OBSIDIAN_VAULT/wiki/index.md"
判断: wiki/projects/${PROJECT_NAME}.md が既に存在する場合は 更新モード。新規作成ではなく既存ページに追記/補強する (既存内容を破壊しない)。
Step 0.5: qmd 検索 (利用可能な場合のみ)
qmd MCP ツール (mcp__qmd__query) が利用可能なら、プロジェクト名や主要ディレクトリ名で事前検索して既存の関連ページを発見する:
mcp__qmd__query(
collection: "brain-wiki",
searches: [{type: "lex", query: "<PROJECT_NAME>"}],
intent: "find existing wiki pages about this project"
)
qmd が使えない/0 件でも失敗扱いにしない。Step 0-3 の ls だけでも重複回避は成立する。
Step 1: プロジェクト全体の俯瞰
以下を順に読む。node_modules, .git, dist, build, .next, .venv, pycache, target, vendor, .DS_Store は除外。
# ファイル全体像
git ls-files 2>/dev/null || find . -type f \
-not -path '*/node_modules/*' \
-not -path '*/.git/*' \
-not -path '*/dist/*' \
-not -path '*/build/*' \
-not -path '*/__pycache__/*' \
-not -path '*/target/*' \
-not -path '*/.venv/*'
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 · 304 lines · 140 tokens per session scan A a1ac6e7ddfda
wiki-ingest-all is a skill published in the GitHub repository megaphone-tokyo/kioku (5 stars, last pushed 2mo ago), licensed MIT. It adds 140 tokens to every session and 3,777 once invoked, about $0.0007 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
instinct-system
Continuous learning system that observes every tool call, learns project patterns, and proactively suggests optimizations. Hook-based, GDPR-aware, and designed to add < 50ms latency to any tool execution.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
exploiting-format-string-vulnerabilities
Methodology for exploiting format string bugs where attacker-controlled data reaches the format argument of printf-family functions, enabling stack/memory disclosure (info leaks for ASLR/PIE/canary defeat) and arbitrary write primitives (%n) to hijack control flow via GOT/.finiarray overwrites.
taiyi-compress
A workflow tool for shrinking large coding-agent conversations and work files into shorter context notes. It can also coordinate separate agents for parallel development and create handoff notes for continuing work in a new session.
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…