aiko-select

aiko-select is a skill for Claude Code from masa-san-jp/Agent-Aiko. It costs 30 tokens per session (1,041 once invoked), scanned A, original, MIT.

A command for switching Aiko to its original personality, the default customizable personality, or a named personality stored in the shared Aiko folder.

In plain words
What is it for?
Use `/aiko-select origin`, `/aiko-select override`, or a named personality such as `work` to select the personality for the session.
Why use it?
It makes it possible to change Aiko’s active personality without manually editing the mode and personality files.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use /aiko-select origin, /aiko-select override, or a named personality such as work to select the personality for the session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/masa-san-jp/agent-aiko/aiko-select
Install

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.

Any agent
npx skills add masa-san-jp/Agent-Aiko --skill aiko-select
Clone the repo
git clone --depth 1 https://github.com/masa-san-jp/Agent-Aiko

Made for: Claude Code.

Wrote 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.

agentmods badge for aiko-select

README.md
[![agentmods](https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/aiko-select/github.svg)](https://agentmods.dev/skills/masa-san-jp/agent-aiko/aiko-select)
Your own site
<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/aiko-select"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/aiko-select/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.

agentmods 80×15 button for aiko-select

Your own site · 80×15
<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/aiko-select"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/aiko-select.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.01041
Opus 5 $0.00015 $0.00521
Sonnet 5 $0.00006 $0.00208
Haiku 4.5 $0.00003 $0.00104

Measured 9d ago against content hash f4252d5cde74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

aiko-select 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.

claude-code/template/.claude/skills/aiko-select/SKILL.md · 86 lines

What it actually says

/aiko-select <name>

人格を切り替えます。

引数パターンと動作

引数 動作
origin modeorigin に、active-persona を空に
override または 引数なし modeoverride に、active-persona を空に
<slug> overrides/<slug>/persona.md が存在すれば modeoverride に、active-persona<slug>

手順

  1. 引数を確認します

  2. origin の場合:

    • ~/.aiko/modeorigin に書き込みます
    • ~/.aiko/active-persona を空にします(Write で空文字列)
    • ロゴを表示して報告します
      アイコ(オリジナル)に切り替えました。プレフィックスは Aiko-origin: です。
      
  3. override または引数なしの場合:

    • ~/.aiko/modeoverride に書き込みます
    • ~/.aiko/active-persona を空にします
    • ロゴを表示して報告します
      アイコ(カスタマイズ)に切り替えました。プレフィックスは Aiko-override: です。
      
  4. その他の <slug> の場合:

    タイポ・大文字小文字の揺れがあってもなんとなく察して解決します。~/.aiko/persona/overrides/ 配下で persona.md を含むディレクトリ名を候補集合として、以下を上から判定し、最初にヒットしたものを採用します。

    段階 判定 動作
    1. 完全一致(大小無視・前後空白除去) normalize 後に完全一致 Workwork 確認なしで切替
    2. 単一の prefix 一致 入力で始まる候補が 1 個 wowork <候補> ですね?」と 1 行確認
    3. 単一の部分一致 入力を含む候補が 1 個 udstudy 同上
    4. 単一の編集距離 ≤ 2 Levenshtein 距離 ≤ 2 の候補が 1 個 worlwork 同上
    5. 複数候補にヒット 2 個以上 wwork / writing 候補列挙して再入力
    6. ヒットなし 0 個 xyz 候補列挙して再入力

    段階 2〜4 の確認:

    「<入力>」は「<候補>」のことですね? 切り替えてよろしいですか?
    

    ユーザー同意で続行、否定なら全候補を列挙して再入力を促します。

    段階 5・6 の応答:

    「<入力>」に該当する人格が <複数 / 見つかり> ません。
    
    候補:
      origin
      ★ <active>
        <slug>
        <slug>
    
    もう一度 /aiko-select <name> で指定してください。
    

    解決後の切替動作:

    • ~/.aiko/modeoverride に書き込みます
    • ~/.aiko/active-persona<slug> に書き込みます(末尾改行あり)
    • ロゴを表示して報告します
      人格「<slug>」に切り替えました。プレフィックスは Aiko-<slug>: です。
      

注意

  • 切替後は次の発話から新しい人格ファイルに従います
  • active-persona ファイルが存在しない場合は Write で新規作成します
Changes

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.

  1. 9d ago First seen · 86 lines · 30 tokens per session scan A f4252d5cde74

Subscribe to this mod's changes

aiko-select is a skill published in the GitHub repository masa-san-jp/Agent-Aiko (3 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,041 once invoked, about $0.0002 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.