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 ysskrishna/ai-agent-skills --skill creative-thinkinggit clone --depth 1 https://github.com/ysskrishna/ai-agent-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/ysskrishna/ai-agent-skills/creative-thinking)<a href="https://agentmods.dev/skills/ysskrishna/ai-agent-skills/creative-thinking"><img src="https://agentmods.dev/badge/skills/ysskrishna/ai-agent-skills/creative-thinking.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00108 | $0.00758 |
| Opus 5 | $0.00054 | $0.00379 |
| Sonnet 5 | $0.00022 | $0.00152 |
| Haiku 4.5 | $0.00011 | $0.00076 |
Grade A, and why
creative-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 8d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Thinking
Defer judgment during divergence. Keep generate (Prime, Diverge, Connect) separate from Harvest (pick and plan).
How to run it with this skill: one clearly headed section per phase in this order: Prime → Diverge → Connect → Harvest. Optional Perspectives beat only when noted in Setup.
Setup (run before starting)
In one short block:
- Creative brief — goal, audience, constraints (time, tone, taboos)
- Default pass — Prime → Diverge → Connect → Harvest (state this line)
If constraints are missing, ask at most 3 clarifying questions in one message, then proceed. Note any remaining gaps or working guesses in plain language (no bracket tags in Setup).
If the user is stuck on one framing, add a short Perspectives beat before Diverge: Optimist / Skeptic / Outsider — two reframes each, no cross-critique yet.
The Phases
Prime
Warm context in 2–4 bullets: what would delight or surprise success look like? What must not be violated?
Diverge
Quantity first. Produce a substantive list of ideas (no fixed count unless the user asks for one). Tag ideas F (flexible reuse of existing), N (novel twist), or W (wild — may be impractical).
Use at least two different creative triggers drawn from: analogy (unrelated domain), constraint flip (remove/add a rule), user fantasy (absurd ideal), time shift (past/future), scale shift (micro/macro).
Connect
Combine or mash ideas: A + B → hybrid concept in several lines (aim for multiple mashups, fewer than Diverge but not a single mashup unless the brief is tiny).
Harvest
- Top picks — 3 ideas with selection rationale tied to the brief
- Next creative step — e.g. prototype storyboard, user interview, spike, moodboard
- Parking lot — 2 promising ideas deferred (why deferred)
Execution Rules
- No harsh criticism in Prime, Diverge, or Connect; park risks for a separate pass if the user asks.
- Do not pretend user research happened; label speculative benefits as hypothetical.
- One response for all phases unless the user requests pacing.
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.
- 8d ago First seen · 77 lines · 108 tokens per session scan A 8012ca0a3c4a
creative-thinking is a skill published in the GitHub repository ysskrishna/ai-agent-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 108 tokens to every session and 758 once invoked, about $0.0005 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.
Other skills, from other repositories
animated-portfolio-sites
Build a one-page animated personal or portfolio site (canvas starfield, rotating galaxies with mouse parallax, hidden accordion/card content, anchor nav) and publish it free on GitHub Pages. Covers the canvas technique and the Pages permission wall, not just one task.
caption-assistant
Writes captions, accessibility alt text, and short image or page descriptions tailored to the visible content and audience. Use when the user asks to "describe this image", "write alt text", "caption this", or needs screen reader text, a11y descriptions, image descriptions, or social captions.
songwriting-and-ai-music
Songwriting craft and Suno AI music prompts.
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.