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 oscarsterling/clelp-skills --skill x-banner-craftgit clone --depth 1 https://github.com/oscarsterling/clelp-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/oscarsterling/clelp-skills/x-banner-craft)<a href="https://agentmods.dev/skills/oscarsterling/clelp-skills/x-banner-craft"><img src="https://agentmods.dev/badge/skills/oscarsterling/clelp-skills/x-banner-craft/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/oscarsterling/clelp-skills/x-banner-craft"><img src="https://agentmods.dev/badge/skills/oscarsterling/clelp-skills/x-banner-craft.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 | $0.00046 | $0.01492 |
| Opus 5 | $0.00023 | $0.00746 |
| Sonnet 5 | $0.00009 | $0.00298 |
| Haiku 4.5 | $0.00005 | $0.00149 |
Grade A, and why
x-banner-craft 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 12d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
X Banner Craft
Actionable playbook for designing X (Twitter) profile header banners that survive real desktop and mobile rendering, not just a full-bleed canvas preview.
Canvas and geometry
- Canvas is always 1500x500px (3:1 source aspect).
- A center safe band of roughly x:150-1350, y:85-415 holds all copy and focal content. Outer margins crop first on mobile and under header chrome.
- Lower-left is the avatar dead zone. The circular avatar overlaps this region (roughly x:0-320, y:260-500). Put nothing essential there.
- Make the avatar pocket the darkest / richest part of the frame so the white avatar ring and white display name snap forward instead of dissolving into the background.
One idea, feed-thumbnail legibility
- One focal idea per banner. Never a collage of products, logos, and slogans.
- If the idea does not read at thumbnail size while scrolling a feed, it fails.
- Treat the banner as a billboard seen in one glance, not a brochure.
Canva-derived craft checklist
These eight cues are distilled from banner-design best practice:
- Limited color palette - two to three intentional tones, not a rainbow.
- Generous negative space - let the idea breathe; do not fill every pixel.
- One clear message - a single setup/payoff beat, not a paragraph.
- Deliberate contrast - dark against light (or reverse) by design, not accident.
- Subtle texture or grain - never a flat-digital wash; a little noise adds depth.
- Blocks of color over busy detail - broad fields beat dense illustration.
- Do not complicate - cut elements until the frame feels inevitable.
- Know when enough is enough - stop before the last "clever" extra.
Also: pair design with photography rather than competing with it. The profile owner's avatar photo is the photography half of that pairing. The banner is the designed stage; the face is the subject.
Contrast-against-the-avatar rule
Before picking a palette, look at the actual avatar photo's value range and hue.
What ships with it
13 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.
- examples/bad_banner.png 925 KB
- examples/bad_banner.regions.json 501 B
- examples/bad/desktop_composite.png 931 KB
- examples/bad/phone_composite.png 313 KB
- examples/demo_banner.png 922 KB
- examples/demo_banner.regions.json 499 B
- examples/demo/desktop_composite.png 932 KB
- examples/demo/phone_composite.png 325 KB
- examples/README.md 1.3 KB
- scripts/bad_sample_spec.json 659 B
- scripts/compose_banner.py 13 KB runs code
- scripts/demo_spec.json 710 B
- scripts/validate_banner.py 9.4 KB runs code
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.
- 12d ago First seen · 145 lines · 46 tokens per session scan A 8b4f8dc3d458
x-banner-craft is a skill published in the GitHub repository oscarsterling/clelp-skills (0 stars, last pushed 5d ago), licensed MIT. It adds 46 tokens to every session and 1,492 once invoked, about $0.0002 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
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.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.