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 mikecann/agent-skills --skill mike-convex-thumbnailgit clone --depth 1 https://github.com/mikecann/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/mikecann/agent-skills/mike-convex-thumbnail)<a href="https://agentmods.dev/skills/mikecann/agent-skills/mike-convex-thumbnail"><img src="https://agentmods.dev/badge/skills/mikecann/agent-skills/mike-convex-thumbnail/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/mikecann/agent-skills/mike-convex-thumbnail"><img src="https://agentmods.dev/badge/skills/mikecann/agent-skills/mike-convex-thumbnail.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 | $0.00073 | $0.02321 |
| Opus 5.5 | $0.00029 | $0.00928 |
| Sonnet 5.5 | $0.00015 | $0.00464 |
| Haiku 4.5 | $0.00007 | $0.00232 |
Grade A, and why
mike-convex-thumbnail 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.
How it starts
The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mike Convex Thumbnail
Create polished YouTube thumbnails for Mike's Convex/dev videos using the image model, Mike's local cutout photos, and local Convex brand assets.
When to Use
- Creating YouTube thumbnail options for a Convex or developer video.
- Reworking the Convex static hosting "NO DASHBOARDS" thumbnail.
- Making a thumbnail that must include Mike's recognizable head-and-shoulders portrait.
- Replacing an incorrect generated mark with the real Convex logo or symbol.
When Not to Use
- Generic thumbnail advice with no image generation requested.
- Non-Convex videos unless Mike explicitly wants the same personal thumbnail style.
- Deterministic compositing in code, unless Mike explicitly asks for a manual layout. The manual collage route looked bad for this style.
Core Workflow
- Inspect the available local references before prompting the image model:
- Run
bash scripts/check-local-assets.shfrom this skill. It discovers the Google Drive account folder and prints absolute paths for the photo and brand assets. - Use
view_imageon at least one Mike headshot and the Convex symbol before calling the image model.
- Run
- If the user provided a script, Notion page, or video brief, extract the main hook first. Keep the thumbnail concept simple enough to read at feed size, and make it intriguing, not descriptive (see "What makes Mike click").
- Use the image model for the thumbnail. Do not build the main image by manually pasting cutouts and cards together unless the user asks for that.
- Keep text short. Prefer one strong phrase such as
NO DASHBOARDS,HOST ON CONVEX,STATIC APP LIVE, orSKIP HOSTING. - Prompt for Mike as a large recognizable head-and-shoulders portrait, not a full-body figure.
- The Convex logo on Mike's cap is usually enough. Don't scatter more Convex logos around the scene. If the concept needs one, pass the real swirl as a reference and replace any cube or hexagon mark the model invents. For a video about a partner's product (Daytona, for example), use the partner's real logo, downloaded from their GitHub or press kit, at the payoff (next to the green tick).
- Return 3 to 5 visually distinct options when brainstorming. If Mike points at one option, iterate that option instead of restarting the set: pass the chosen draft as the first reference and say "keep everything the same, change only ...".
What ships with it
4 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 · +30 lines 5c6e68f95d01
- 27d ago Changed · +38 lines deeeda076201
- 2mo ago First seen · 135 lines · 73 tokens per session scan A e003a0b8d538
mike-convex-thumbnail is a skill published in the GitHub repository mikecann/agent-skills (21 stars, last pushed 23d ago), licensed MIT. It adds 73 tokens to every session and 2,321 once invoked, about $0.0003 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.