six-thinking-hats

six-thinking-hats is a skill for Claude Code from ysskrishna/ai-agent-skills. It costs 157 tokens per session (1,450 once invoked), scanned A, original, MIT.

A six-part thinking method from Edward de Bono that examines one question through separate roles for facts, feelings, risks, benefits, new ideas, and process control.

In plain words
What is it for?
Running a structured discussion or analysis with the six hats, then combining the factual, emotional, critical, positive, creative, and organizing perspectives.
Why use it?
It keeps different kinds of thinking from being mixed together, so a group can examine the same issue from distinct viewpoints.

Skill for Claude Code

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

Part of the ai-agent-skills plugin — 10 skills shipped together

Good fit Running a structured discussion or analysis with the six hats, then combining the factual, emotional, critical, positive, creative, and organizing perspectives.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ysskrishna/ai-agent-skills/six-thinking-hats
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 ysskrishna/ai-agent-skills --skill six-thinking-hats
Clone the repo
git clone --depth 1 https://github.com/ysskrishna/ai-agent-skills

Made for: Claude Code.

Or install ai-agent-skills, the plugin that ships this one along with the rest of its 10 skills.

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 six-thinking-hats

README.md
[![agentmods](https://agentmods.dev/badge/skills/ysskrishna/ai-agent-skills/six-thinking-hats/github.svg)](https://agentmods.dev/skills/ysskrishna/ai-agent-skills/six-thinking-hats)
Your own site
<a href="https://agentmods.dev/skills/ysskrishna/ai-agent-skills/six-thinking-hats"><img src="https://agentmods.dev/badge/skills/ysskrishna/ai-agent-skills/six-thinking-hats/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 six-thinking-hats

Your own site · 80×15
<a href="https://agentmods.dev/skills/ysskrishna/ai-agent-skills/six-thinking-hats"><img src="https://agentmods.dev/badge/skills/ysskrishna/ai-agent-skills/six-thinking-hats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,450 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 $0.00157 $0.01450
Opus 5 $0.00078 $0.00725
Sonnet 5 $0.00031 $0.00290
Haiku 4.5 $0.00016 $0.00145

Measured 12d ago against content hash ac262ce182f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

six-thinking-hats 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 12d 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/six-thinking-hats/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Six Thinking Hats

Six Thinking Hats (Edward de Bono) is a parallel thinking method for a single focus question. Rather than mixing logic, emotion, optimism, and critique in one back-and-forth, the thinker or group takes six complementary roles in sequence, all wearing the “same hat” at each step. That keeps facts, gut reactions, risks, upsides, and new ideas from talking past each other.

Each hat’s meaning, constraints, and bullet formats are defined once in The Hats; the closing Blue pass is in Blue Synthesis.

How to run it with this skill: one hat per section, clearly labelled; never mix two hats in the same section; always close with Blue synthesis that integrates earlier hats and adds no new facts, risks, ideas, or recommendations beyond what those hats produced.


Setup (run before starting)

Before executing hats, establish in one short block:

  1. Focus question — one sentence
  2. Mode — which hat set (see table below); default: Full
  3. Depth — how much detail per hat (see table below); default: Standard
  4. Hat order — list the sequence you'll follow

If critical information is missing, ask at most 3 questions in one message, then proceed. Note any remaining gaps or working guesses in plain language (no bracket tags in Setup).


Modes

Mode Hats Use for
Full (default) Blue → White → Red → Black → Yellow → Green → Blue Broad decisions, full-spectrum reasoning
Creative Blue → Green → Yellow → Red → Blue Idea generation; skips Black to avoid premature criticism
Risk Blue → White → Black → Blue Risk scans and failure prevention
Decision Blue → White → Black → Yellow → Blue Go/no-go decisions; skips Red and Green
Custom User-defined + Blue at end User-directed; confirm order before starting

Custom mode: only the six standard hats are allowed. Blue synthesis is always required at the end — add it silently if the user omits it.

Read the full file on GitHub · 147 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. 12d ago First seen · 147 lines · 157 tokens per session scan A ac262ce182f8

Subscribe to this mod's changes

six-thinking-hats is a skill published in the GitHub repository ysskrishna/ai-agent-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 157 tokens to every session and 1,450 once invoked, about $0.0008 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.