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 OutlineDriven/odin-claude-plugin --skill thumbnail-accuracy-scorecardgit clone --depth 1 https://github.com/OutlineDriven/odin-claude-pluginWrote 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/outlinedriven/odin-claude-plugin/thumbnail-accuracy-scorecard)<a href="https://agentmods.dev/skills/outlinedriven/odin-claude-plugin/thumbnail-accuracy-scorecard"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/thumbnail-accuracy-scorecard/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/outlinedriven/odin-claude-plugin/thumbnail-accuracy-scorecard"><img src="https://agentmods.dev/badge/skills/outlinedriven/odin-claude-plugin/thumbnail-accuracy-scorecard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.01082 |
| Opus 5 | $0.00017 | $0.00541 |
| Sonnet 5 | $0.00007 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
thumbnail-accuracy-scorecard 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 4d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thumbnail accuracy scorecard
Contract
| Field | Bound contract |
|---|---|
| Trigger | Thumbnail concepts need real-size, accuracy-first scoring without misleading claims. |
| Authority | Human-gated: asks for asset approval before rendering approved assets; otherwise reversible local: writes only named local artifacts; rollback is undo. No remote mutation. |
| Side effect | Accuracy-gated thumbnail scorecard with per-dimension scores and an immutable receipt. |
| Done | One accurate winner and two accurate runners-up clear the fixed rubric threshold. |
| Stop | No accurate winner; approval blocked; budget exhausted. Bound: platform, audience, rubric, assets, round cap. |
Inputs
- Bound (required): platform (YouTube, Twitter/X, LinkedIn, etc.), audience, rubric definition, assets to score, and round cap.
- Fixed rubric definition (required): the accuracy dimensions, their weights, the per-dimension scale, the aggregate threshold, and the tie-breaking rule. Frozen before any scoring.
- Platform dimensions (required): the exact pixel dimensions at which thumbnails are rendered for the target platform (for example, 1280x720 for YouTube). Sourced from the platform's published thumbnail specification, not guessed.
Fixed rubric
| Dimension | Weight | Criterion (0 to 10 scale) |
|---|---|---|
| Claim accuracy | 0.30 | The thumbnail text and imagery accurately represent the content. No exaggerated claims, misleading titles, or false implications. |
| Visual clarity | 0.25 | The subject is recognizable at the target platform's display size. Text is legible at thumbnail dimensions, not just at full resolution. |
| Composition fidelity | 0.20 | The layout matches the platform's safe-zone constraints. No critical elements are cropped or obscured by platform UI overlays. |
| Color and contrast | 0.15 | The color palette and contrast are appropriate for the platform and do not mislead about the content tone. |
| Brand consistency | 0.10 | The thumbnail aligns with the creator or product brand identity. |
What ships with it
1 file 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.
- 4d ago First seen · 57 lines · 34 tokens per session scan A f80636ef953c
thumbnail-accuracy-scorecard is a skill published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 1,082 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 2026-09-06.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…