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 magnus919/agent-skills --skill youtube-thumbnailgit clone --depth 1 https://github.com/magnus919/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/magnus919/agent-skills/youtube-thumbnail)<a href="https://agentmods.dev/skills/magnus919/agent-skills/youtube-thumbnail"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/youtube-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/magnus919/agent-skills/youtube-thumbnail"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/youtube-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 | $0.00074 | $0.01323 |
| Opus 5.5 | $0.00030 | $0.00529 |
| Sonnet 5.5 | $0.00015 | $0.00265 |
| Haiku 4.5 | $0.00007 | $0.00132 |
Grade A, and why
youtube-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 17d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube thumbnail design
Make the right viewer curious about a real promise the video fulfills. A thumbnail is packaging, not a performance guarantee: earn attention without misrepresenting the video, and judge the result by qualified viewing rather than clicks alone.
When not to use
Use this skill for YouTube thumbnail strategy and production. For general channel positioning or growth plans, use a channel-strategy skill. For artwork that is not a YouTube preview card, use the relevant image, brand, or publication skill instead.
Workflow
-
Ground the promise in the video. Inspect the supplied video, outline, transcript, title, and available image assets before inventing a concept. If the video itself is accessible, use an appropriate transcript/video capability. Write one sentence for what the video actually delivers, who should care, and what evidence or moment in the video proves it. If those facts are missing and cannot be found, ask a small number of targeted questions; do not fill gaps with invented stakes, people, outcomes, or scenes.
-
Design the title–thumbnail package. Keep the actual title beside every concept. State what the title explains and what the image adds. The image may create a question, reveal a striking result, show a meaningful contrast, or evoke a fitting emotion; it should not merely repeat the title. Text is optional, not a quota. Add it only when it makes the idea clearer or more distinctive at thumbnail size.
-
Build a reference board, then translate. Gather several references from the creator's own videos, relevant channels, adjacent formats, and non-YouTube visual culture. For each, record the mechanism that earns attention (for example, scale contrast, reveal, gesture, visual metaphor, or an unresolved question), not just its colors or layout. Adapt the mechanism to this video's proof and audience; do not copy another creator's composition, branding, artwork, or likeness. Read design principles when the brief needs deeper concept development.
What ships with it
11 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.
- evals/evals.json 6.1 KB
- evals/trigger-queries.json 713 B
- README.md 3.1 KB
- references/design-principles.md 6.3 KB
- references/platform-and-policy.md 5.5 KB
- references/testing-and-measurement.md 5.1 KB
- requirements.txt 17 B
- scripts/test_thumbnail_preflight.py 5.0 KB runs code
- scripts/thumbnail_preflight.py 11 KB runs code
- templates/experiment-log.md 1007 B
- templates/thumbnail-brief.md 2.3 KB
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.
- 17d ago First seen · 67 lines · 74 tokens per session scan A c2934f2a509b
youtube-thumbnail is a skill published in the GitHub repository magnus919/agent-skills (133 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,323 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 2026-10-01.
Other skills, from other repositories
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
spec
Enter the Spec phase of CocoBrew. Guides the developer through structured requirements capture: goal, success criteria, constraints, personas involved, data sources, and deliverables. Writes spec.md to .cocoplus/lifecycle/ and creates a git commit.
discuss
Run a structured decision-capture dialogue before $plan — locks implementation choices (model, evaluation methodology, accuracy threshold, scope boundaries) into discuss.md to prevent silent decision drift during planning. Supports --red-team flag for adversarial post-PASS challenge session.
cocoharvest
Decompose an approved plan into parallel workstreams, assign specialist personas, classify stages as HITL or AFK (CocoLens), generate flow.json stages with checkpoints and dual-file state, and create per-stage prompt files. Includes adaptive parallelism, stall detection, shell identity injection, and consecutive…
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
bloom
Run a structured four-question working-backwards dialogue before $spec — commits the developer to the outcome (beneficiary, core capability, constraints, press release) before specification begins, anchoring all downstream phases to the original intent.