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.
npx skills add deciqAI/knowledge-skills --skill lateral-thinkinggit clone --depth 1 https://github.com/deciqAI/knowledge-skillsWrote 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/skills/deciqai/knowledge-skills/lateral-thinking)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/lateral-thinking"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-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.
<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/lateral-thinking"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/lateral-thinking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00112 | $0.02213 |
| Opus 5.5 | $0.00045 | $0.00885 |
| Sonnet 5.5 | $0.00022 | $0.00443 |
| Haiku 4.5 | $0.00011 | $0.00221 |
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 23d 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.
This is a copy
88% identical to work-item-refinement — 158 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lateral Thinking
Overview
Lateral thinking is the discipline of solving problems by approaching them from unexpected angles — not by going deeper along an existing logical path but by moving sideways to a new starting point. Coined by Edward de Bono, it converts creative leaps into learnable, repeatable techniques: assumption challenge, random entry, concept extraction, and PO (Provocative Operation). The brain is a pattern-forming system — lateral thinking deliberately disrupts those patterns to make invisible solutions visible.
Compose with neighbors: Use first-principles before lateral thinking to clear inherited assumptions. Use six-thinking-hats after to evaluate ideas generated (Green Hat = lateral thinking space). Use inversion as a lightweight lateral move when time is short.
When to Use
Use when: team cycles through the same 2–3 options; an industry assumption has gone years untested; someone says "think outside the box / we need a breakthrough / how might we / we've tried everything"; solution space feels exhausted despite good problem definition.
When NOT: problem has a mathematical optimum; decision needed in under 5 min; team lacks domain knowledge (use first-principles first); task requires rigorous proof.
Coaching Novices (Adaptive Front Door)
- Engine mode: user brings a specific stuck problem → run The Process directly.
- Coach mode: user signals unfamiliarity or asks "what is this / how does it work?" → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- One-line what-it-is: lateral thinking is about starting from a different place, not going deeper on the same path — four specific techniques, not hoping inspiration strikes.
- Check fit against When to Use / When NOT to use — if the problem has a clear optimal answer, redirect; if time is very short, offer inversion instead.
- Elicit their real stuck problem. "We need to be more innovative" is not workable; "our checkout conversion hasn't improved in 18 months despite A/B testing" is.
[WAIT — do not advance until user responds]
- Walk through assumption challenge → random entry → concept extraction → PO one at a time. Pose each technique as a question and wait before advancing.
[WAIT — do not advance until user responds]
- Close by naming the specific assumption or pattern they broke. The cognitive move is more valuable than any single idea it produced.
[WAIT — do not advance until user responds]
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 23d ago Changed 3286e3374e2c
- 2mo ago First seen · 123 lines · 112 tokens per session scan A df11615313be
lateral-thinking is a skill published in the GitHub repository deciqAI/knowledge-skills (16 stars, last pushed 23d ago), licensed MIT. It adds 112 tokens to every session and 2,213 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to work-item-refinement, differing in 158 lines, and is treated as a copy.
lateral-thinking compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| lateral-thinkingdeciqAI/knowledge-skills | Skill | 16 | 23d ago | MIT | A | 112 | Claude Code, Codex |
| ai-adoption-leadalebgl77/claude-inc | Skill | 24 | 6d ago | MIT | A | 72 | Claude Code |
| compliance-checkalebgl77/claude-inc | Skill | 24 | 6d ago | MIT | A | 98 | Claude Code |
| ui-ux-pro-maxalebgl77/claude-inc | Skill | 24 | 6d ago | MIT | A | 102 | Claude Code |
| cto-advisoralebgl77/claude-inc | Skill | 24 | 6d ago | MIT | A | 0 | Claude Code |
| ai-seoalebgl77/claude-inc | Skill | 24 | 6d ago | MIT | A | 114 | Claude Code |
| journal-entryalebgl77/claude-inc | Skill | 24 | 6d ago | MIT | A | 103 | Claude Code |