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 kioku-delegation-handoffgit 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/kioku-delegation-handoff)<a href="https://agentmods.dev/skills/megaphone-tokyo/kioku/kioku-delegation-handoff"><img src="https://agentmods.dev/badge/skills/megaphone-tokyo/kioku/kioku-delegation-handoff/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/kioku-delegation-handoff"><img src="https://agentmods.dev/badge/skills/megaphone-tokyo/kioku/kioku-delegation-handoff.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 | $0.00190 | $0.05670 |
| Opus 5 | $0.00095 | $0.02835 |
| Sonnet 5 | $0.00038 | $0.01134 |
| Haiku 4.5 | $0.00019 | $0.00567 |
Grade A, and why
kioku-delegation-handoff 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.
How it starts
The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kioku-delegation-handoff
PM session が他 Claude session (制作 Claude / codex CLI / マーケ Claude) に impl / strategic / marketing task を委譲する handoff doc 作成 を skill 化。N=6 delegation cycles で固化した template + LEARN convention を 1 commands で展開、scope-specific 部分のみ手動入力で済ませる。
いつ使うか
- 制作 Claude session に impl task を委譲したい時 (bugfix / new feature / refactor / test infra 等)
- codex CLI session に strategic doc / 探索系 task を委譲したい時 (roadmap 執筆 / 競合分析 / scope 検討)
- マーケ Claude session に article / publish task を委譲したい時 (release narrative / SNS post / community comm)
使わない場面:
- PM session 直接 impl が経済的な scope (LEARN#7 「小 task < 4h、1-2 file」zone) → handoff overhead が impl より大きく ROI 逆転
- 既に main に存在する task (LEARN#10 逆方向: 必ず
git log -10 origin/main --onelineで先 verify) - main hygiene 違反 state (LEARN#12 Rule 2:
git log --oneline origin/main..mainが non-empty) → 先に local commit を retroactive PR 化
前提 (handoff 作成前 mandatory)
- LEARN#12 Rule 2 main hygiene clean:
git log --oneline origin/main..mainが empty - LEARN#10 逆方向 precheck pass: 委譲予定 task が main に既存しないことを
git log -10 origin/main --onelineで verify - target session type が確定: 制作 Claude / codex / マーケ のどれか
- PM 側 LEARN#10 precheck 完了: 委譲する spec の対象 file / function / line が現コードで verify 済 (handoff 内の "PM 側 LEARN#10 precheck 結果" table に記載するため)
起動
/kioku-delegation-handoff <scope-topic> # default --to=制作 Claude
/kioku-delegation-handoff <scope-topic> --to=制作
/kioku-delegation-handoff <scope-topic> --to=codex
/kioku-delegation-handoff <scope-topic> --to=マーケ
例:
/kioku-delegation-handoff v0-7-3-readme-mode-based-setup
/kioku-delegation-handoff v0-8-phase-d-visualizer-pivot-decision --to=codex
/kioku-delegation-handoff v0-7-2-marketing-articles --to=マーケ
出力 path
tools/claude-brain/handoff/YYMMDDNN_<scope-topic>-delegation.md
YY: 年下 2 桁 (例: 26)
MM: 月 2 桁
DD: 日 2 桁
NN: 同日 N 件目の連番 (01, 02, ...)
例: 26050702_v0-7-3-readme-mode-based-setup-delegation.md (= 2026-05-07 の 2 件目)
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.
- 12d ago First seen · 370 lines · 190 tokens per session scan A 4b1aeb2af92c
kioku-delegation-handoff is a skill published in the GitHub repository megaphone-tokyo/kioku (5 stars, last pushed 2mo ago), licensed MIT. It adds 190 tokens to every session and 5,670 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.
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…