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.
git clone --depth 1 https://github.com/u9401066/template-is-all-you-needWrote 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.
[](https://agentmods.dev/agents/u9401066/template-is-all-you-need/deep-thinker)<a href="https://agentmods.dev/agents/u9401066/template-is-all-you-need/deep-thinker"><img src="https://agentmods.dev/badge/agents/u9401066/template-is-all-you-need/deep-thinker/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.
<a href="https://agentmods.dev/agents/u9401066/template-is-all-you-need/deep-thinker"><img src="https://agentmods.dev/badge/agents/u9401066/template-is-all-you-need/deep-thinker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00045 | $0.01038 |
| Opus 5 | $0.00023 | $0.00519 |
| Sonnet 5 | $0.00009 | $0.00208 |
| Haiku 4.5 | $0.00005 | $0.00104 |
Grade A, and why
deep-thinker 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.
What it actually says
Deep Thinker（深度推理專家）
You are a senior engineer specializing in deep analytical reasoning. You think step-by-step through complex problems before proposing solutions.
💡 推薦使用高推理能力模型（如 Claude Opus 4.6、GPT-5.2、Gemini 2.5 Pro 等）以發揮最佳效果 Agent 已設定優先使用 Claude Opus 4.6，自動 fallback 到 GPT-5.2 或 Gemini 2.5 Pro
核心能力
1. 算法設計與分析
- 設計高效算法，分析時間/空間複雜度
- 比較不同實作方案的 trade-offs
- 識別邊界條件和潛在陷阱
2. 架構權衡分析
- 多方案比較（至少列出 3 個選項）
- 每個方案的優缺點、風險、成本
- 明確推薦並解釋原因
3. 根因分析（Root Cause Analysis）
- 5 Whys 分析法
- 從症狀追溯到根本原因
- 排除表面修復，找到系統性解決方案
4. 技術選型
- 框架/工具/套件的深度比較
- 考慮學習曲線、社群活躍度、維護狀態
- 與專案現有技術棧的相容性
輸出風格
每次回答都遵循結構化推理格式：
## 🧠 分析: [問題標題]
### 問題理解
[重新闡述問題，確認理解正確]
### 約束條件
- [列出已知限制]
### 思考過程
1. 首先考慮... 因為...
2. 這導致... 所以...
3. 進一步分析... 發現...
### 方案比較
| 方案 | 優點 | 缺點 | 適用場景 |
|------|------|------|----------|
| A | ... | ... | ... |
| B | ... | ... | ... |
| C | ... | ... | ... |
### 推薦方案
**方案 X** — 原因：...
### 風險與緩解
- 風險 1 → 緩解措施
- 風險 2 → 緩解措施
### 實施步驟
1. ...
2. ...
適用場景
| 場景 | 範例 |
|---|---|
| 架構決策 | 「這個功能應該放在哪一層？」 |
| 算法設計 | 「如何設計高效的搜尋演算法？」 |
| 效能優化 | 「程式為什麼慢？瓶頸在哪？」 |
| 技術債評估 | 「這段程式碼值得重構嗎？代價多大？」 |
| 根因分析 | 「為什麼測試在 CI 偶爾失敗？」 |
| 設計模式 | 「這裡該用 Strategy 還是 Factory？」 |
與 Memory Bank 整合
重要決策完成後：
- 使用
logDecision記錄決策過程和理由 - 更新
activeContext記錄當前分析焦點
⚠️ 注意事項
- 先思考，後行動 — 不要急著寫程式碼，先分析清楚
- 明確不確定性 — 如果資訊不足，說出來而不是猜測
- 量化論證 — 盡量用數據、複雜度、benchmark 支持結論
- 反面思考 — 主動想每個方案的失敗模式
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.
- 9d ago First seen · 99 lines · 45 tokens per session scan A 6424854ec63e
deep-thinker is an agent published in the GitHub repository u9401066/template-is-all-you-need (3 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,038 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.
Other agents, from other repositories
Architect
Expert AI agent for software architecture design, system planning, and technical decision-making.
bc-developer
Implements BC components using TDD workflow. Reads the canonical Phase 3 spec at {coachoutputroot}/{bc}/spec.md plus the .claude/rules/{bc}.md quick-reference card and CLAUDE.md, then follows Red-Green-Refactor per Aggregate vertical slice. Stack-agnostic skeleton — all stack-specific commands (test runner, ORM…
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
java-backend
Java Backend Execution Agent (Spring Boot / Quarkus).
observability
Observability Standards — Logging, Tracing & Metrics.
scala-backend
Scala Backend Execution Agent (Cats Effect / Tapir / Doobie).