deep-think

deep-think is a skill for Claude Code, Codex from rongarede/claude-skills-research. It costs 64 tokens per session (1,274 once invoked), scanned A, original, MIT.

A structured method for thinking through difficult or uncertain problems in several stages. It examines assumptions, different viewpoints, longer-term effects, and confidence in the final conclusion.

In plain words
What is it for?
Use it for major architecture decisions, strategy, ethical questions, multi-party trade-offs, and subtle debugging problems. It is also intended for problems with consequences over many months.
Why use it?
It helps when the first obvious answer may be incomplete, or when several choices involve important trade-offs. It makes the reasoning behind a decision easier to inspect.

Skill for Claude CodeCodex

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

Good fit Use it for major architecture decisions, strategy, ethical questions, multi-party trade-offs, and subtle debugging problems. It is also intended for problems with consequences over many months.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rongarede/claude-skills-research/deep-think
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 rongarede/claude-skills-research --skill deep-think
Clone the repo
git clone --depth 1 https://github.com/rongarede/claude-skills-research

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/rongarede/claude-skills-research/deep-think/github.svg)](https://agentmods.dev/skills/rongarede/claude-skills-research/deep-think)
Your own site
<a href="https://agentmods.dev/skills/rongarede/claude-skills-research/deep-think"><img src="https://agentmods.dev/badge/skills/rongarede/claude-skills-research/deep-think/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.

agentmods 80×15 button for deep-think

Your own site · 80×15
<a href="https://agentmods.dev/skills/rongarede/claude-skills-research/deep-think"><img src="https://agentmods.dev/badge/skills/rongarede/claude-skills-research/deep-think.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,274 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 $0.00064 $0.01274
Opus 5 $0.00032 $0.00637
Sonnet 5 $0.00013 $0.00255
Haiku 4.5 $0.00006 $0.00127

Measured 10d ago against content hash 6ce2ea76af46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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/deep-think/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deep Think

Extended deliberation skill for problems that resist quick answers. Forces multi-step reasoning, considers second-order effects, and produces well-justified conclusions.

Trigger Words

  • /deep-think
  • "think deeply about"
  • "reason through this"
  • "what are the second-order effects"
  • "this is a hard problem"
  • "deliberate on"
  • "think step by step"

When to Use

  • Architectural decisions with 6+ month consequences
  • Trade-offs where multiple options seem equally valid
  • Problems where the obvious answer might be wrong
  • Multi-stakeholder decisions with conflicting interests
  • Ethical or philosophical dimensions
  • Debugging subtle, hard-to-reproduce issues
  • Strategy formulation under uncertainty

Core Process

Deep Think Progress:
- [ ] Step 1: Problem decomposition
- [ ] Step 2: Assumption surfacing
- [ ] Step 3: Multi-perspective analysis
- [ ] Step 4: Second-order effects mapping
- [ ] Step 5: Synthesis and conclusion
- [ ] Step 6: Confidence calibration

Step 1: Problem Decomposition

Break the problem into its constituent parts:

## Problem Statement
[Restate the problem in your own words]

## Sub-Problems
1. [Component A] — [why it matters]
2. [Component B] — [why it matters]
3. [Component C] — [why it matters]

## Dependencies
- [A] depends on [B] because...
- [C] is independent of [A/B]

Step 2: Assumption Surfacing

Explicitly list every assumption:

## Assumptions (must be stated explicitly)

| # | Assumption | Type | If Wrong, Impact |
|---|-----------|------|------------------|
| 1 | [assumption] | [factual/value/scope] | [consequence] |
| 2 | [assumption] | [factual/value/scope] | [consequence] |

Challenge each assumption:

  • Is this actually true, or do we just believe it?
  • What evidence supports/contradicts this?
  • What if the opposite were true?

Step 3: Multi-Perspective Analysis

Analyze from at least 3 different viewpoints:

## Perspectives

### Perspective 1: [Role/Viewpoint]
- Sees the problem as: [framing]
- Prioritizes: [values]
- Would decide: [choice]
- Reasoning: [chain]

### Perspective 2: [Role/Viewpoint]
[same structure]

### Perspective 3: Devil's Advocate
- The strongest argument against the emerging consensus is: [argument]
- Evidence supporting this counter-view: [evidence]
- This matters because: [reason]

Read the full file on GitHub · 188 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. 10d ago First seen · 188 lines · 64 tokens per session scan A 6ce2ea76af46

Subscribe to this mod's changes

deep-think is a skill published in the GitHub repository rongarede/claude-skills-research (2 stars, last pushed 5mo ago), licensed MIT. It adds 64 tokens to every session and 1,274 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.