lateral-thinking

lateral-thinking is a skill for Claude Code from ysskrishna/ai-agent-skills. It costs 124 tokens per session (750 once invoked), scanned A, original, MIT.

A structured idea-generation method for escaping fixed ways of thinking. It uses provocations, extracted principles, a range of related concepts, and candidate ideas.

In plain words
What is it for?
Reframing difficult problems, challenging implicit rules, and generating alternative approaches when ideation has stalled.
Why use it?
It helps when a problem has become stuck around the same assumptions or familiar solutions.

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 Reframing difficult problems, challenging implicit rules, and generating alternative approaches when ideation has stalled.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ysskrishna/ai-agent-skills/lateral-thinking
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 lateral-thinking
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 lateral-thinking

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/ysskrishna/ai-agent-skills/lateral-thinking"><img src="https://agentmods.dev/badge/skills/ysskrishna/ai-agent-skills/lateral-thinking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 750 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 $0.00124 $0.00750
Opus 5 $0.00062 $0.00375
Sonnet 5 $0.00025 $0.00150
Haiku 4.5 $0.00012 $0.00075

Measured 10d ago against content hash 220fe74ab086, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

lateral-thinking 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/lateral-thinking/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lateral Thinking

Movement before judgment. Treat provocative lines as stepping stones, not final positions.

How to run it with this skill: one clearly headed section per move in the default order from Setup (Provocation (Po) → Extract principle → Concept fan → Candidates), or the alternate path the user chose.


Setup (run before starting)

In one short block:

  1. Stuck point — what pattern or assumption feels rigid?
  2. Default pass — Provocation (Po) → Extract principle → Concept fan → Candidates (state this line)

If safety or legal constraints are unclear, ask at most 3 questions in one message before generating provocations. Note any remaining gaps in plain language (no bracket tags in Setup).

If the user asks for random stimulus instead of a Po, replace the Provocation step with Random entry: one random noun or image, then several bridges (property → analogy → mechanism → application) into ideas.

If the user asks to challenge implicit rules, replace Provocation / Extract principle / Concept fan with: list implicit rules → for each, Challenge / Reframe / Test (smallest experiment) → Escape (two ways to sidestep the load-bearing rule) → then Candidates only from that thread.


The Moves

Provocation

Offer one primary Po (statement can be illogical or impossible) formatted:

Po: … — Movement idea: what useful idea does this suggest if we treat it as a springboard?

Extract principle

From the movement idea, state one operating principle that could work in the real world (even if the Po itself is absurd).

Concept fan

Widen from the principle along three directions — broaden, deepen, redirect — with several branches per direction unless the user wants more.

Candidates

Several actionable ideas. Tag each: near-term / stretch / experimental.


Execution Rules

  1. Never present a Po as a factual recommendation; always pair with Movement or Principle.
  2. If a provocation touches safety, ethics, or law, stop and surface the conflict explicitly — do not rationalize harm.
  3. One response for all moves unless interactive pacing is requested.

Read the full file on GitHub · 79 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 · 79 lines · 124 tokens per session scan A 220fe74ab086

Subscribe to this mod's changes

lateral-thinking is a skill published in the GitHub repository ysskrishna/ai-agent-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 124 tokens to every session and 750 once invoked, about $0.0006 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.