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 0xBeycan/genesis --skill ideategit clone --depth 1 https://github.com/0xBeycan/genesisWrote 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/0xbeycan/genesis/ideate)<a href="https://agentmods.dev/skills/0xbeycan/genesis/ideate"><img src="https://agentmods.dev/badge/skills/0xbeycan/genesis/ideate/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/0xbeycan/genesis/ideate"><img src="https://agentmods.dev/badge/skills/0xbeycan/genesis/ideate.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00100 | $0.00524 |
| Opus 5.5 | $0.00040 | $0.00210 |
| Sonnet 5.5 | $0.00020 | $0.00105 |
| Haiku 4.5 | $0.00010 | $0.00052 |
Grade A, and why
ideate 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 2mo 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.
What it actually says
Ideate — diverge before you converge
An agent's default failure is that the first workable idea wins. This skill is the antidote: a short, deliberate divergence step before a commitment — never instead of one.
When to use
Decisions with real design freedom: a product or feature angle, a name, a design-language direction, an architecture fork with several viable shapes, a debugging dead-end. Also whenever the user asks for alternatives.
When not to use: implementation style (boring wins — ponytail),
decisions already constrained to one viable shape, reversible trivia.
Steps
- Fix the constraints first. What MUST hold (from
AGENTS.md, the vision, the budget)? Constraints are not options — write them down. - Generate 3–5 genuinely different options — different shapes, not variants of one; include one deliberate wildcard from outside the obvious pattern. Search the web if the space is unfamiliar.
- Score against the constraints and goals — one line per option, honest costs included.
- Converge to ONE. Say why it wins, in a sentence.
- Record the rejects: a
docs/memory/decisions.mdline; an ADR when the fork was real (write-adr). Rejected alternatives are the highest-signal part of the record.
Notes
- Division of labor:
clean-code= the shape of code ·ponytail= the amount of code ·ideate= the option space before the commitment. They chain, never clash: ideate picks the what; ponytail minimizes the how. - Diverge on the WHAT, stay boring on the HOW.
- Time-boxed: this is a step, not a session. If the options don't meaningfully differ, say so and move on — forced variety is noise.
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.
- 2mo ago First seen · 43 lines · 100 tokens per session scan A 51b68e7d2d43
ideate is a skill published in the GitHub repository 0xBeycan/genesis (12 stars, last pushed 3mo ago), licensed MIT. It adds 100 tokens to every session and 524 once invoked, about $0.0004 per session on Opus 5.5. 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.