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 agentmods add skills/masa-san-jp/agent-aiko/tasknpx skills add masa-san-jp/Agent-Aiko --skill taskgit 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/task)<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/task"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/task.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 | $0.00150 | $0.01190 |
| Opus 5 | $0.00075 | $0.00595 |
| Sonnet 5 | $0.00030 | $0.00238 |
| Haiku 4.5 | $0.00015 | $0.00119 |
Grade A, and why
task 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 5d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/task
残タスク管理スキル。プロジェクトの残タスク正本である tasks.json（配置先は自分の構成に合わせる。以下 <TASKS_JSON> と表記）を読み書きする。
詳細な運用ルールはタスクディレクトリの README.md に置く想定。
基本原則
<TASKS_JSON>が唯一の正本。他のメモ・ドキュメント・ロール設定に別途タスク一覧を作らない- 読みも書きも必ずこのスキルを経由する（直接編集してもよいが、ID 規則と重複チェックを破らないこと）
サブコマンド
/task list [filters]
<TASKS_JSON> から残タスクを読み出す。
引数なし：status が open または in_progress のタスクを priority 昇順 → created 降順で表示。
フィルタ例：
/task list status:open— open のみ/task list status:in_progress— 着手中のみ/task list source:<source-name>— 特定 source/task list source:<sourceA>,<sourceB>— 複数 source/task list agent:owner— assignee 指定/task list priority:<=2— priority 2 以下（高優先のみ）- 複数フィルタは AND 結合
出力形式：
T-2026W20-<source>-001 [open] (P2) [owner] タスクのタイトル
source: <source-name>
created: 2026-05-17
notes: ...（1 行サマリ）
/task add
新規タスクを追記。インタラクティブに以下を確認：
- title（必須）：簡潔なタイトル
- source（必須）：既存 source から選ぶか新規作成（source 名はプロジェクトで定義する分類ラベル）
- agent（必須）：assignee（
ownerがデフォルト） - priority（任意）：1-5、デフォルト 3
- notes（任意）：背景・経緯
- review_ref（任意）：関連レビュー ID または外部ドキュメントパス
ID 採番：T-<ISO-week>-<source>-<NNN> を自動生成
- ISO-week：当日の ISO 週番号（例：2026-05-17 → 2026W20）
- NNN：同一週・同一 source の最大 NNN + 1（ゼロ埋め 3 桁）
created：当日の YYYY-MM-DD
status：open で開始
/task update <id>
既存タスクの status／notes／priority／agent を更新する。
notesへの追記は[YYYY-MM-DD] 内容プレフィクスで時系列を保つ（既存 notes に append）statusをdoneに変える場合は/task closeを使う（completed 日付の自動付与のため）
/task close <id>
status を done に遷移、completed に当日日付を入れ、必要なら notes に完了経緯を追記する。
status: close-as-skipped にしたい場合は /task update <id> で明示的に指定。
実装ノート
<TASKS_JSON>は手書きしやすい JSON。Python のjson.load／json.dump（ensure_ascii=False, indent=2）で読み書きする想定- 同時編集ロックは特に持たない（単一ユーザー前提。マルチユーザーなら排他制御を足す）
- diff を見やすく保つため、フィールドの順序は schema 順（id → title → agent → priority → status → source → review_ref → created → notes → completed）
関連ファイル
- 正本：
<TASKS_JSON>（プロジェクト直下のタスク JSON） - ルール本体：タスクディレクトリの
README.md - ルール目次：プロジェクトのルール索引ドキュメント（あれば）
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.
- 5d ago First seen · 87 lines · 150 tokens per session scan A a4f3314c2771
task is a skill published in the GitHub repository masa-san-jp/Agent-Aiko (3 stars, last pushed 1mo ago), licensed MIT. It adds 150 tokens to every session and 1,190 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
canvas
Display HTML content — games, visualizations, dashboards, generated HTML, interactive demos — on a connected canvas-capable display surface. Use when you need to present visual or interactive web content on a screen.
share-skills
Use when you need to author, package, or share a skill folder — understanding the SKILL.md format, where skills live, and how to bundle a folder so it can be shared with others.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
git-commit
Stage, write, and structure git commits and pull requests cleanly. Read this before committing — for conventional-commit message format, when to split commits, and how to open a PR with the gh CLI.
optimizer
Analyzes and automatically optimizes existing agents by improving system prompts and tool configuration.
app_evaluator
A professional skill for App Evaluation (evaluating app's performance with score) and App Improvement (giving professional suggestions for improving the app's performance).