voice-decide

voice-decide is a skill for Claude Code from yukurash/16minds-plugin. It costs 117 tokens per session (1,283 once invoked), scanned A, original, MIT.

A decision tool that chooses between multiple options using the judgment style of one of 16 personality types. It gives a decision and explains the reasoning, with optional detail about risks and rejected choices.

In plain words
What is it for?
It helps choose between plans, release strategies, tools, or other alternatives when a specific personality-based perspective is requested.
Why use it?
It removes the need to leave a set of options undecided when a particular viewpoint is useful. It also makes the values and trade-offs behind the choice explicit.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents.

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

Good fit It helps choose between plans, release strategies, tools, or other alternatives when a specific personality-based perspective is requested.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yukurash/16minds-plugin/voice-decide
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 yukurash/16minds-plugin --skill voice-decide
Clone the repo
git clone --depth 1 https://github.com/yukurash/16minds-plugin

Made for: Claude Code.

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 voice-decide

README.md
[![agentmods](https://agentmods.dev/badge/skills/yukurash/16minds-plugin/voice-decide.svg)](https://agentmods.dev/skills/yukurash/16minds-plugin/voice-decide)
Your own site
<a href="https://agentmods.dev/skills/yukurash/16minds-plugin/voice-decide"><img src="https://agentmods.dev/badge/skills/yukurash/16minds-plugin/voice-decide.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,283 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 $0.00117 $0.01283
Opus 5 $0.00059 $0.00642
Sonnet 5 $0.00023 $0.00257
Haiku 4.5 $0.00012 $0.00128

Measured 8d ago against content hash 3a5c7cecf461, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

voice-decide 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.

skills/voice-decide/SKILL.md · 86 lines

What it actually says

ユーザーが voice-decide Skill を発動しました。目的: 指定人格として、提示された選択肢から1つを選び、その人格の価値観で理由を述べる。

引数の解釈

引数 $ARGUMENTS から以下を取り出す:

  1. 人格タイプ: 16タイプのいずれか1つ。未指定なら聞き返す。
  2. モード:
    • --mode=light: 決断1行 + 理由1〜2文(既定: 即答用途)
    • --mode=middle: 決断 + 理由3〜5文 + リスク認識
    • --mode=heavy: 決断 + 理由 + 採用しなかった選択肢への評価 + 撤回条件
  3. 選択肢: 残りの文字列から A) ... B) ... C) ... 形式、または箇条書き、または「Xか、Yか、Zか」のような自然言語形式で抽出する。最低2つ必要。
  4. 文脈情報: 選択肢以外の前提条件(期限、制約、目的など)があれば、それも subagent に渡す。

エラー処理

  • 選択肢が1つ以下の場合:
    Usage: <人格> で決めるには2つ以上の選択肢が必要です。
    Example: 「ENTJで決めて。A) 来月リリース、機能8割 B) 再来月リリース、機能100%」
    
  • 人格指定が無い場合: 利用可能タイプを出して聞き返す。
  • 不明なタイプ名・モード: エラーを返して終了。

実行: 該当人格 subagent を Task で1回呼び出す

Task ツールで、指定された人格の subagent を1回呼び出す。subagent への入力には以下を含める:

subagent に渡す本文

あなたは指定された人格として、以下の選択肢から1つを選んでください。中立・保留・「ケースバイケース」のような逃げは禁止です。あなたの価値観で必ず1つに決めてください。

【選択肢】:
<ここに選択肢を列挙>

【前提条件・文脈】(あれば):
<期限・制約・目的など>

【出力フォーマット】(モードによって変える):

light モード出力フォーマット指定

decision: <選択肢のラベル(A/B/C など)。1文字または短いタグで>
reasoning: <なぜこれを選んだか。あなたの価値観の軸が見える1〜2文で。あなたの口調を保つ>

middle モード出力フォーマット指定

decision: <選択肢のラベル>
reasoning: <あなたの価値観からその決断に至る筋道を3〜5文で。あなたの口調で>
risk: <この決断で取りこぼすもの・将来後悔しうる点を1〜2文で>

heavy モード出力フォーマット指定

decision: <選択肢のラベル>
reasoning: <あなたの価値観からその決断に至る筋道を5〜8文で。あなたの口調で>
rejected:
  - <選択肢X>: <なぜこれを選ばなかったか、しかし何がこの案の良い点だったかを1〜2文で>
  - <選択肢Y>: <同上>
risk: <この決断で取りこぼすもの・将来後悔しうる点を2〜3文で>
revisit_when: <どんな状況変化が起きたらこの決断を撤回すべきかを1〜2文で>

出力

subagent が返した内容を そのまま 表示する。先頭に ### <TYPE>(<mode>)の決断 のような見出しを1行だけ付けてよい。

決断の中立化(要約や中和)は一切行わない。人格の偏りこそがこの Skill の価値。

注意

  • 1つの選択肢を必ず選ばせること。subagent が「両方良い」「決められない」のような出力をした場合は、再度プロンプトを送って強制的に1つに絞らせる。
  • 他人格との比較を聞かれたら、別タイプを引数に取って再実行を提案する。
  • 既存の /mind コマンドは「意見を聞く」用途。こちらは「決断を強制する」用途であり、出力の射程が異なる。
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. 8d ago First seen · 86 lines · 117 tokens per session scan A 3a5c7cecf461

Subscribe to this mod's changes

voice-decide is a skill published in the GitHub repository yukurash/16minds-plugin (5 stars, last pushed 14d ago), licensed MIT. It adds 117 tokens to every session and 1,283 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens