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 masa-san-jp/Agent-Aiko --skill routinegit clone --depth 1 https://github.com/masa-san-jp/Agent-AikoWrote 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/masa-san-jp/agent-aiko/routine)<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/routine"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/routine.svg" alt="Measured on agentmods" 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 | $0.00103 | $0.01376 |
| Opus 5 | $0.00051 | $0.00688 |
| Sonnet 5 | $0.00021 | $0.00275 |
| Haiku 4.5 | $0.00010 | $0.00138 |
Grade A, and why
routine scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/routine
リポジトリに記録された定期実行タスクを手動で確認・実行する入口の参考実装。パス・名称は各組織の構成に合わせて調整して使う。
対象は 2 種類:
- メタエージェント — このパッケージの
meta/run-meta-pendingと同じ仕組み(reviewer / scout / lab / janitor 等) - 組織固有の定期ジョブ — 各組織が用意する任意のパイプライン(データ収集・レポート生成・外部同期など)。ジョブ名・mode は自分の実装に置き換える
引数
| コマンド | 何をするか | 外部への影響 |
|---|---|---|
/routine / /routine status |
メタエージェントの最終実行時刻と、登録済み定期ジョブの状態を表示 | 読み取りのみ |
/routine meta <role> |
メタエージェント(reviewer / scout / lab / janitor / all)を手動実行 |
ログと last-run を更新 |
/routine <job> [mode] |
組織固有の定期ジョブを手動実行(<job> は自分で定義) |
ジョブ次第(下記の注意参照) |
引数なしの /routine は /routine status と同じ。第 1 引数の status と meta は予約語なので、<job> 名には使えない(衝突を避けるため別名を付ける)。
/routine status
メタエージェントと登録済み定期ジョブの状態を確認する。
# メタエージェントの last-run / pending(自環境のメタ構成に合わせる)
for role in reviewer scout lab janitor; do
last="{{ORG_REPO_PATH}}/Agent-team/logs/reviews/.last-run-$role"
pending="{{ORG_REPO_PATH}}/Agent-team/logs/reviews/.pending/$role"
if [ -f "$last" ]; then
ts=$(cat "$last" 2>/dev/null)
last_str=$(date -r "$ts" '+%Y-%m-%d %H:%M' 2>/dev/null || echo "$ts")
else
last_str="未起動"
fi
[ -f "$pending" ] && pend=" (pending)" || pend=""
echo "$role: $last_str$pend"
done
# 組織固有ジョブの状態(例。自分のジョブの status コマンドに置き換える)
# cd "{{ORG_REPO_PATH}}/Agent-team/tools/<job>" && python3 run.py status
必要に応じて <tasks-file>(例:tasks.json)のうち定期実行由来の項目も確認する。
/routine meta <role|all>
メタエージェントを手動起動する。role は reviewer / scout / lab / janitor / all。手順は /meta と同じ。完了後は必ず last-run を更新し pending を消す:
date +%s > "{{ORG_REPO_PATH}}/Agent-team/logs/reviews/.last-run-<role>"
rm -f "{{ORG_REPO_PATH}}/Agent-team/logs/reviews/.pending/<role>"
/routine <job> [mode] — 組織固有の定期ジョブ
各組織が用意した定期ジョブを手動で叩く汎用パターン。ジョブは {{ORG_REPO_PATH}}/Agent-team/tools/<job>/ 配下に置き、run.py <mode> などのエントリで実行する想定。
cd "{{ORG_REPO_PATH}}/Agent-team/tools/<job>"
python3 run.py <mode> # 例:status / collect / build / sync / all など、ジョブが定義する mode
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.
- 8d ago First seen · 85 lines · 103 tokens per session scan A ce429f01c41a
routine is a skill published in the GitHub repository masa-san-jp/Agent-Aiko (3 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,376 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
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
google-calendar
Google Calendar via gws: list events, create, accept, find free time.
google-drive
Google Drive via gws: search, list, upload, download, share.
google-forms
Google Forms via gws: create forms, add items, read responses.
google-meet
Google Meet via gws: create spaces, fetch join links, list recordings.
phone-call
Place outbound AI phone calls via Bland AI: book reservations, make appointments, ask businesses questions, then report back the transcript and summary.