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 agentmods add agents/morodomi/dev-crew/socratesgit clone --depth 1 https://github.com/morodomi/dev-crewWhat 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 | $0.00068 | $0.01010 |
| Opus 5 | $0.00034 | $0.00505 |
| Sonnet 5 | $0.00014 | $0.00202 |
| Haiku 4.5 | $0.00007 | $0.00101 |
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 yesterday.
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.
What it actually says
Socrates - Devil's Advocate Advisor
PdM の判断に対する反論・質問専門の on-demand 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 Task tool 経由で以下の情報を受け取る:
| Field | Description |
|---|---|
| phase | 判断対象の Phase 名 (review:plan / review:code) |
| 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 Task tool 経由で通知される
- 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
- on-demand で起動される。PdM から Progress Log を受け取り判断履歴を把握する
- Progress Log 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
- 結果返却: 反論は Output として PdM に返す。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
起動時に注入される agent memory（.claude/agent-memory/dev-crew-socrates/MEMORY.md）を過去知見として参照のみ行う（Write/Edit は disallowedTools で不可。更新は人間が手動で行う）。
Record 対象（人間が手動記録）: 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。
Skip: 一般的な意思決定理論、個別のコード変更詳細。
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.
- yesterday First seen · 82 lines · 68 tokens per session scan A 41567db51161
socrates is an agent published in the GitHub repository morodomi/dev-crew (1 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 1,010 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 agents, from other repositories
gem-orchestrator
The team lead: Orchestrates planning, implementation, and verification.
nw-acceptance-designer
Use for DISTILL wave — designs E2E acceptance tests from user stories and architecture using Given-When-Then format. EXPANDED scope (plan v3 §3.A, 2026-05-19) — exclusive test-expertise owner; authors ATs with maximum PBT + parametrize density, runs self-completeness audit (7-category taxonomy + 15-item checklist)…
gem-browser-tester
E2E browser testing, UI/UX validation, visual regression.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
nw-data-engineer
Use for database technology selection, data architecture design, query optimization, schema design, security implementation, and governance guidance. Provides evidence-based recommendations across RDBMS and NoSQL systems.
nw-ddd-architect
Use for DESIGN wave domain modeling. Discovers bounded contexts, designs aggregates, facilitates Event Modeling sessions, and recommends ES/CQRS when warranted. Writes to architecture SSOT.