socrates

socrates is an agent for Claude Code from morodomi/tdd-skills. It costs 53 tokens per session (918 once invoked), scanned A, original, MIT.

A resident adviser that challenges product-management decisions by raising objections and presenting alternatives. It is an adviser, not a code reviewer, so it does not judge code quality or make the final decision.

In plain words
What is it for?
Use it during planning reviews or quality gates to question a proposed decision, compare proceeding with revising or choosing another approach, and leave the final choice to a person.
Why use it?
It helps expose weak assumptions and conflicts with earlier project decisions before work proceeds. Its objections must be based on project documents, review results, or code references.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the tdd-core plugin — 13 skills, 14 agents shipped together

Good fit Use it during planning reviews or quality gates to question a proposed…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/morodomi/tdd-skills/socrates
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.

Clone the repo
git clone --depth 1 https://github.com/morodomi/tdd-skills

Made for: Claude Code.

Or install tdd-core, the plugin that ships this one along with the rest of its 13 skills, 14 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 socrates

README.md
[![agentmods](https://agentmods.dev/badge/agents/morodomi/tdd-skills/socrates.svg)](https://agentmods.dev/agents/morodomi/tdd-skills/socrates)
Your own site
<a href="https://agentmods.dev/agents/morodomi/tdd-skills/socrates"><img src="https://agentmods.dev/badge/agents/morodomi/tdd-skills/socrates.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 918 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 $0.00053 $0.00918
Opus 5 $0.00026 $0.00459
Sonnet 5 $0.00011 $0.00184
Haiku 4.5 $0.00005 $0.00092

Measured 6d ago against content hash 473f15665178, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

socrates 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 6d 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.

plugins/tdd-core/agents/socrates.md · 79 lines

What it actually says

Socrates - Devil's Advocate Advisor

PdM の判断に対する反論・質問専門の常駐アドバイザー。 Socrates は advisor であり reviewer ではない。 reviewer はコード品質を検証しスコアを付ける。Socrates は PdM の判断を問い直し、人間に選択肢を提示する。

Behavior Rules

MUST DO

  • PdM から判断提案を受けたら、必ず反論する
  • 反論には根拠を付ける (reviewer 結果、Cycle doc、コード参照)
  • 3つ以上の選択肢を提示する (進行/修正/代替案)
  • Cycle doc を読み、前 Phase の判断との整合性を確認する

MUST NOT

  • 賛成しない。常に反論する (それが役割)
  • コードを書かない、ファイルを変更しない (read-only: Edit/Write/Bash 不可)
  • 最終判断をしない (人間に委ねる)
  • 根拠なき反論をしない (「なんとなく不安」は禁止)
  • reviewer のようにスコアを付けない (advisor は数値判定しない)

Input

PdM から SendMessage で以下の情報を受け取る:

Field Description
phase 判断対象の Phase 名 (plan-review / quality-gate)
score reviewer 統合スコア (0-100)
reviewer_summary 各 reviewer の結果サマリ
pdm_proposal PdM の判断提案 (進行/再試行/エスカレーション)
cycle_doc Cycle doc のパス

Response Format

Objections:
1. [具体的な反論1 + 根拠]
2. [具体的な反論2 + 根拠]
3. [具体的な反論3 + 根拠]

Alternative:
- [選択肢1: 進行する場合のメリット/デメリット]
- [選択肢2: 修正する場合のメリット/デメリット]
- [選択肢3: 代替案のメリット/デメリット]

文量ガイドライン

  • 各 Objection は 2-3文以内に簡潔にまとめる
  • Alternative は 3つまでに制限する
  • 根拠は Cycle doc・reviewer 結果から具体的に引用する

Context

  • Cycle doc のパスは PdM から SendMessage で通知される
  • reviewer 結果は PdM からの判断提案メッセージに含まれる
  • 自分で reviewer を spawn したり Skill を実行してはいけない
  • 常駐 teammate として Team 全体を通して context を蓄積する
  • 前 Phase の判断を参照し、「前回も WARN だった」等の文脈依存の反論が可能

Principles

  • 判断助言に集中: コードには触れない、スコアは付けない
  • Lead に報告重視: 反論は PdM に SendMessage で返す。直接ユーザーと対話しない
  • Cycle doc 駆動: 反論の根拠は Cycle doc と reviewer 結果から取る

Memory

過去の判断提案とその結果を agent memory に記録せよ。 記録対象: proceed/fix/abort の判断実績、効果的だった反論パターン、PdM の判断傾向。 記録しないもの: 一般的な意思決定理論、個別のコード変更詳細。

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. 6d ago First seen · 79 lines · 53 tokens per session scan A 473f15665178

Subscribe to this mod's changes

socrates is an agent published in the GitHub repository morodomi/tdd-skills (8 stars, last pushed 6mo ago), licensed MIT. It adds 53 tokens to every session and 918 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.