deep-think

deep-think is a skill for Claude Code, Codex from wangyendt/wayne-skills. It costs 109 tokens per session (1,391 once invoked), scanned A, original, MIT.

A workflow for deeply analysing a problem through explicit planning, focused follow-up analysis, prediction, reflection, and a final summary.

In plain words
What is it for?
Use it when someone asks for a thorough breakdown, careful consideration, a detailed plan, or a systematic analysis.
Why use it?
It adds structure when a short answer is not enough and helps keep complex reasoning tied to the original goal.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

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 skills/wangyendt/wayne-skills/deep-think
Any agent
npx skills add wangyendt/wayne-skills --skill deep-think
Clone the repo
git clone --depth 1 https://github.com/wangyendt/wayne-skills

Made for: Claude Code, Codex.

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 deep-think

README.md
[![agentmods](https://agentmods.dev/badge/skills/wangyendt/wayne-skills/deep-think.svg)](https://agentmods.dev/skills/wangyendt/wayne-skills/deep-think)
Your own site
<a href="https://agentmods.dev/skills/wangyendt/wayne-skills/deep-think"><img src="https://agentmods.dev/badge/skills/wangyendt/wayne-skills/deep-think.svg" alt="Measured on agentmods" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,391 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 5.1 $0.00109 $0.01391
Opus 5 $0.00055 $0.00696
Sonnet 5 $0.00022 $0.00278
Haiku 4.5 $0.00011 $0.00139

Measured 6d ago against content hash 949c748bb54e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

deep-think 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.

deep-think/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Think (ReAct-Plan Framework)

When This Skill Activates

Trigger when user requests deeper analysis beyond surface-level responses:

  • "帮我深入思考", "请仔细分析", "帮我详细拆解", "请梳理一下思路"
  • "深入理解", "仔细考虑", "详细分析"

Core Philosophy

Think Globally, Act Locally, Reflect Continuously

  • Explicit Planning: Create structured plan before execution
  • Dynamic Re-planning: Update plan after new insights emerge
  • Prediction: Anticipate outcomes before diving in
  • Reflection: Assess progress and update belief state

Output Structure

1. Initial Planning (P0)

## 初始规划

**核心问题**: [简述]

**目标**: [成功标准]

**已知**: [关键事实 1-3 条]

**关键未知**: [需要弄清 1-3 条]

**计划 P0**:
1. [阶段 1: 步骤 1-2]
2. [阶段 2: 步骤 1-2]
3. [阶段 3: 步骤 1-2]

2. Iterative Deep Dives (2-4 次)

Keep it concise! 每个迭代聚焦一个核心维度:

## 思考:[主题]

**问题**: [当前步骤的不足或新发现的问题]

**分析**: [1-2 句关键分析]

**新发现**: [简列 1-2 条]

**计划更新**:
- [阶段 X]: [新增/修改的内容]
  - [子要点]

重要原则:

  • 只显示变化的部分,不要重复整个计划
  • 每个迭代 10-15 行以内
  • 聚焦关键发现,避免细节堆砌

3. Final Synthesis

## 最终综合

**核心发现** (3-5 条核心洞察):
1. [发现 1]
2. [发现 2]

**最终计划**:
- 阶段 1: [步骤 1, 2] ([关键细节])
- 阶段 2: [步骤 1, 2, 3] ([关键细节])
- 阶段 3: [步骤 1, 2] ([关键细节])

**关键成功因素** (3 条):
- [因素 1]
- [因素 2]

**主要风险**:
- [风险 1] → [应对]
- [风险 2] → [应对]

Conciseness Guidelines

避免这样做 建议这样做
完整重复之前的计划 只显示变化部分
长篇分析解释 1-2 句直击要点
细节过多堆砌 提炼关键信息
迭代次数过多 2-4 次迭代即可
最终计划重复前文 精炼总结,聚焦变化

Example

## 初始规划

**核心问题**: 如何到达火星

**目标**: 安全送达火星并返回

**计划 P0**:
1. 发射火箭
2. 飞往火星
3. 着陆火星

## 思考:运载能力

**问题**: "发射火箭"太笼统,未考虑载荷和燃料

**分析**: 地火转移需 50-100 吨载荷,单次发射无法满足

**新发现**: 需要轨道加油,多次发射补给燃料

**计划更新**:
- 阶段 1: 增加轨道加油能力

## 思考:时间窗口

**问题**: 未考虑返程窗口

**分析**: 需在火星停留 500 天等返程窗口

**新发现**: 任务总时长约 3 年

**计划更新**:
- 新增 阶段 4: 火星停留 (~500 天)
- 新增 阶段 5: 返程

## 思考:生存与 ISRU

**问题**: 返程燃料从哪来?

**分析**: 无法从地球携带,必须就地生产

**新发现**: 利用火星 CO₂ 生产甲烷+氧气

**计划更新**:
- 阶段 2: 增加 货运先行,运送 ISRU 设备
- 阶段 4: 增加 ISRU 生产返程燃料

## 最终综合

**核心发现**:
1. 轨道加油和货运先行是必需策略
2. ISRU 就地生产燃料是返程关键
3. 任务总时长约 3 年

**最终计划**:
- 阶段 1: 技术开发 (运载+着陆+ISRU)
- 阶段 2: 货运先行 (4 艘船预置基础设施)
- 阶段 3: 载人发射 (轨道加油 → 地火转移 200 天)
- 阶段 4: 火星停留 (500-800 天,生产燃料+探索)
- 阶段 5: 返程 (200 天返回地球)

**关键成功因素**:
- Starship 达到设计载荷
- ISRU 无故障运行
- 生命保障维持 3 年

**主要风险**:
- 着陆失败 → 货运先行验证
- ISRU 产能不足 → 增加设备,延长停留期

Read the full file on GitHub · 172 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. 6d ago First seen · 172 lines · 109 tokens per session scan A 949c748bb54e

Subscribe to this mod's changes

deep-think is a skill published in the GitHub repository wangyendt/wayne-skills (8 stars, last pushed 9d ago), licensed MIT. It adds 109 tokens to every session and 1,391 once invoked, about $0.0005 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

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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 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