minds

minds is a command for coding agents from yukurash/16minds-plugin. It costs 56 tokens per session (2,561 once invoked), scanned A, original, MIT.

A command that gathers opinions from multiple role-played personality types and combines them into one response. It supports choosing the discussion mode, types, and output file.

In plain words
What is it for?
Use `/minds` to compare personality-based opinions, limit which types participate, choose response depth, or save the result.
Why use it?
It reduces the need to ask each perspective separately when you want a range of viewpoints on one topic.

Command

Part of the 16-minds plugin — 4 skills, 4 commands, 16 agents shipped together

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.

agentmods
npx agentmods add commands/yukurash/16minds-plugin/minds
Clone the repo
git clone --depth 1 https://github.com/yukurash/16minds-plugin

Or install 16-minds, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 16 agents.

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 minds

README.md
[![agentmods](https://agentmods.dev/badge/commands/yukurash/16minds-plugin/minds.svg)](https://agentmods.dev/commands/yukurash/16minds-plugin/minds)
Your own site
<a href="https://agentmods.dev/commands/yukurash/16minds-plugin/minds"><img src="https://agentmods.dev/badge/commands/yukurash/16minds-plugin/minds.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,561 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00056 $0.02561
Opus 5 $0.00028 $0.01281
Sonnet 5 $0.00011 $0.00512
Haiku 4.5 $0.00006 $0.00256

Measured 3d ago against content hash 887857eae223, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

minds 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 3d 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.

commands/minds.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ユーザーが /minds を実行しました。

引数: $ARGUMENTS

引数の解釈

以下のフラグを取り出し、残りを「お題」とする。

  • --mode=light|middle|heavy--mode light 形式も可): 既定 middle
  • --types=intj,enfp,...: カンマ区切りで対象タイプを限定。指定がなければ全16タイプ。
  • --n=N: 数値。--types 未指定時は16タイプから先頭N個(一覧順)を使う。--types 指定時は --n は無視する。
  • --save: 実行結果を Outputs/<timestamp>-minds-<mode>.md に保存する。
  • --out=<path>: 保存先を明示指定(--save を暗黙的に有効化)。

利用可能なタイプ一覧(一覧順): intj, intp, entj, entp, infj, infp, enfj, enfp, istj, isfj, estj, esfj, istp, isfp, estp, esfp

エラー処理

  • お題が空の場合:
    Usage: /minds [--mode=light|middle|heavy] [--types=a,b,...] [--n=N] [--save] [--out=<path>] <topic>
    Example: /minds AIによるコードレビューの是非
    Example: /minds --mode=heavy --types=intj,enfp,istp このアーキテクチャ案
    Example: /minds --save Qiita記事のタイトル候補
    
  • 未知のタイプ名が --types に含まれる場合は、その旨を伝えて利用可能タイプを返して終了。
  • モード名が不正な場合も同様に終了。

実行フロー

モードによって段階が変わる。フェーズ間で対象agent群への呼び出しは必ず並列(同一メッセージ内で複数のTaskツール呼び出し)で行うこと。

Phase 1(全モード共通): 全タイプの light パス

対象タイプ全員(既定16)を 並列に Task ツールで呼び出す。各 subagent には、お題と light モード出力フォーマット指定を渡す。

light モード出力フォーマット指定(subagentに渡す本文):

お題に対し、以下の4行のみで答えてください。挨拶・前置き・まとめは一切不要です。

score: <1〜5の整数。あなたの価値観から見た総合評価。5=完全賛成、3=条件付き、1=完全反対>
stance: <一行の立場宣言>
key_axis: <判断に最も効いたあなたの価値観の軸(あなたの人格定義に出てくる言葉で)>
concern: <あなたの価値観から見た最大の懸念を一行>

全員の結果が出揃ったら、見やすい表として整形して表示する:

### 全タイプの一次評価

| type | score | stance | key_axis | concern |
|---|---|---|---|---|
| intj | 4 | ... | ... | ... |
...

Phase 2(middle / heavy のみ): 発散意見の深掘り

Phase 1 の結果を見て、意見が割れた/極端だった/他と異なる視点を持っていた タイプを 3〜5 個選ぶ。選定基準は以下のいずれか:

  • score が分布の両端(最も賛成・最も反対)
  • key_axis が他と被っていない独自の軸を提示している
  • concern が他のタイプが見落としている視点を含む

選んだタイプ群を 並列に Task ツールで再度呼び出し、middle モード出力フォーマットで深掘りさせる。

middle モード出力フォーマット指定(subagentに渡す本文):

お題に対し、以下の構成で約150〜250字で答えてください。あなたの口調を必ず保ってください。挨拶・前置き・まとめは不要です。

stance: <一行の立場宣言>
reasoning: <あなたの価値観からその立場に至る筋道を2〜3文で。あなたの口調で>
watchpoint: <あなたの価値観から見た見落としやすい点・推しポイント・引っかかりを1〜2文で>

結果を以下のように表示:

### 深掘り(middle)

#### <TYPE>
<出力をそのまま>

Read the full file on GitHub · 181 lines

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. 3d ago First seen · 181 lines · 0 tokens per session scan A 887857eae223

Subscribe to this mod's changes

minds is a command published in the GitHub repository yukurash/16minds-plugin (5 stars, last pushed 10d ago), licensed MIT. It adds 56 tokens to every session and 2,561 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.