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 agentmods add skills/danium/lateral-thinking/lateralnpx skills add danium/lateral-thinking --skill lateralgit clone --depth 1 https://github.com/danium/lateral-thinkingWhat 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 | $0.00138 | $0.01248 |
| Opus 5 | $0.00069 | $0.00624 |
| Sonnet 5 | $0.00028 | $0.00250 |
| Haiku 4.5 | $0.00014 | $0.00125 |
Grade A, and why
lateral 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lateral
What this does
Being stuck has shapes. Ideas that all feel the same is a different problem from a constraint that feels unbreakable, which is different again from suspecting you are solving the wrong problem. Each shape has a technique that fits it.
This skill diagnoses the symptom, picks exactly one technique, and runs it inline. It is a router, not a technique of its own.
Decision table
| Symptom | Technique |
|---|---|
| Ideas all feel the same; brainstorm output is predictable | random-stimulus |
| A constraint or rule feels unbreakable | provocation |
| Requirements assume things nobody has questioned | inversion |
| We might be solving the wrong problem | concept-fan |
| The solution works but feels derivative | analogy |
| We have one idea and need variations | scamper |
| A decision is being made too fast / everyone agrees | six-hats |
| Everything feels timid, safe, cautious | worst-idea |
Routing procedure
- Diagnose. Match the user's symptom to the table. If the symptom is unclear, ask exactly one focused question — do not interrogate.
- Pick exactly one technique. Never route to a second technique in the same pass. If another looks promising, offer it as a next move once the first has finished.
- Read
../<technique>/SKILL.md— relative to this file — and follow it inline. Do not invoke it as a separate skill; read the file and execute its workflow yourself, including its honesty mechanics. - Refuse analytical work politely. Debugging, code review, and implementation are not creative targets. Suggest an analytical approach instead. Redesigning or ideating about such a process is a valid creative target: "reinvent our code-review ritual" is in scope; "review this PR" is not.
If the target itself is unclear, the chosen technique's own Step 1 will ask for it. Do not ask twice.
If the technique file is missing
A partial install may leave this router without its siblings. Do not fail — run a degraded session from the condensed core loop below, then tell the user:
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.
- 2d ago First seen · 66 lines · 138 tokens per session scan A 055a38b0f7c7
lateral is a skill published in the GitHub repository danium/lateral-thinking (286 stars, last pushed 1mo ago), licensed MIT. It adds 138 tokens to every session and 1,248 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
creative-ideation
Structured brainstorming sessions using proven ideation techniques.
idea-refine
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when starting from a vague idea, brainstorming a new feature, exploring design space, or stress-testing a plan before committing. Trigger phrases: "ideate", "refine this idea", "stress-test my plan", "ideate on".
idea-generator
Use when the user asks for an idea generator, conceptual crossbreeding, mutation, evolution, recombination of existing ideas, or novel concepts derived from unlike sources; also use for follow-ups that evolve, cross, or lock elements of previously generated ideas. Do not trigger for generic brainstorming with no…
brainstorming
Creative ideation and structured brainstorming with multiple methodologies.
skill-ideation
Generate agent skill ideas through problem-driven brainstorming. Situation-specific, narrow-but-universal. Triggers when user wants skill ideas or needs to expand their skill collection.
weaver-mind
Cross-domain bridge thinking for stuck founders, creators, and builders. Finds pattern bridges from unrelated fields — biology, game design, physics, jazz, architecture, logistics — and maps them to your situation with explicit reasoning, pros/cons, and a first experiment. Use when stuck, plateaued, can't get…