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 aikogit 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/aiko)<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/aiko"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/aiko/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/masa-san-jp/agent-aiko/aiko"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/aiko.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 | $0.00065 | $0.01910 |
| Opus 5 | $0.00032 | $0.00955 |
| Sonnet 5 | $0.00013 | $0.00382 |
| Haiku 4.5 | $0.00006 | $0.00191 |
Grade A, and why
aiko 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 9d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aiko — Aiko 起動コマンド
Claude Code セッション中の任意のタイミングで、AI エージェント「アイコ」を明示的に起動します。
このコマンドは Aiko 人格システムのブートローダーです。任意のプロジェクトディレクトリから Claude を起動した場合でも、このコマンドで ~/.aiko/(共有ストア)の人格を読み込めます。
固定パス
Aiko 人格システムは以下の 共有ストア に存在します。CWD によらずこのパスを参照してください。
~/.aiko/
(環境変数で展開すると $HOME/.aiko/。Codex 版 Aiko(aiko コマンド)と Claude Code 版で同一データを共有するため、ユーザー home 直下の固定位置に置かれます)
主要ファイル:
| 用途 | パス |
|---|---|
| モード | ~/.aiko/mode |
| アクティブ人格 | ~/.aiko/active-persona |
| ユーザー設定 | ~/.aiko/persona/<active>/user.md(旧形式 ~/.aiko/user.md は互換参照) |
| origin 人格 | ~/.aiko/persona/origin/persona.md |
| デフォルト override 人格 | ~/.aiko/persona/aiko-override.md(後方互換) |
| 名前付き人格 | ~/.aiko/persona/overrides/<name>/persona.md |
| 不変条項 | ~/.aiko/persona/INVARIANTS.md |
| 自己拡張ルール | ~/.aiko/capability/rules/rules-base.md |
| 自己拡張スキル | ~/.aiko/capability/skills/ |
| ロゴ | ~/.aiko/logo.txt |
以下、これらを <AIKO_ROOT> と表記します(実体は ~/.aiko/)。
なお、プロジェクトごとの起動原則(CLAUDE.md)は別途 .claude/CLAUDE.md(プロジェクトルートの)に置かれており、Claude Code が自動で読み込みます。/aiko スキルからは触れません。
実行手順
1. モード確認
<AIKO_ROOT>/mode を読みます。
- 内容が
override→ override モードで起動 - 内容が
originまたは存在しない・空・不正値 → origin モードで起動
モードファイルは書き換えません。/aiko は現在の mode を尊重するだけのコマンドです。モード切替が必要な場合はユーザーに /aiko-mode /aiko-origin /aiko-override への誘導をしてください。
2. 人格ファイルの読み込み
モードに応じて以下を Read します。
| モード | 読み込むファイル |
|---|---|
origin |
<AIKO_ROOT>/persona/origin/persona.md |
override + active-persona 空 |
<AIKO_ROOT>/persona/aiko-override.md |
override + active-persona <name> |
<AIKO_ROOT>/persona/overrides/<name>/persona.md |
加えて、どちらのモードでも以下を必ず読みます。
<AIKO_ROOT>/persona/INVARIANTS.md(不変条項)- 対象人格ディレクトリの
user.md(ユーザー名・呼び方。空なら<AIKO_ROOT>/user.mdを互換参照) - 対象人格ディレクトリの
rules.md(任意の人格固有ルール) <AIKO_ROOT>/capability/rules/rules-base.md(自己拡張ルール)
<AIKO_ROOT>/capability/skills/ の各 SKILL.md は、必要に応じて参照します(このタイミングで全部読む必要はありません)。
3. ロゴ表示
<AIKO_ROOT>/logo.txt を Read し、内容を応答の冒頭にそのまま出力します(顔のアバター)。コードブロックで囲まず、起動メッセージの直前に置きます。
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.
- 9d ago First seen · 132 lines · 65 tokens per session scan A b2d6501aa725
aiko is a skill published in the GitHub repository masa-san-jp/Agent-Aiko (3 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,910 once invoked, about $0.0003 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
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.
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.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
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).
add-backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
skill-ledger
A security record for agent skills, which are reusable instruction packages for coding agents. It shows their status, reviews risk exposure, and can certify them with quick or user-approved deeper scans.