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 hashgraph-online/awesome-codex-plugins --skill vidseeds-thumbnailsgit clone --depth 1 https://github.com/hashgraph-online/awesome-codex-pluginsWrote 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/hashgraph-online/awesome-codex-plugins/vidseeds-thumbnails)<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/vidseeds-thumbnails"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/vidseeds-thumbnails.svg" alt="Measured on agentmods" 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 | $0.00060 | $0.00898 |
| Opus 5 | $0.00030 | $0.00449 |
| Sonnet 5 | $0.00012 | $0.00180 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
vidseeds-thumbnails 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 yesterday.
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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thumbnails (MCP)
Quick generate → retrieve
vidseeds_get_seed_balance(free).vidseeds_generate_thumbnail→jobId,expectedCostSeeds; pollvidseeds_get_thumbnail_jobevery ~3s (~70–100s typical). Price per image uses model-specific seeds (Gemini 7, OpenAI 11, Grok 3); see get_seed_balance.vidseeds_get_thumbnailorvidseeds_list_thumbnailsfor URLs/ids.- Optional:
vidseeds_download_thumbnail_bundlefor a packaged download.
Edit pricing (2026-06 correct): vidseeds_edit_thumbnail (and restyle) charges model-specific seeds; edits that reference an input image cost more than pure generation (input + output). Check vidseeds_get_seed_balance for current per-model rates before calling. Always confirm with user.
Edit or restyle an existing thumbnail
vidseeds_edit_thumbnail- chat-style edit (async job; poll per tool response).vidseeds_restyle_thumbnail- style transfer on an existing asset.
Attach to a project
vidseeds_apply_thumbnail_to_projectwithprojectIdand the generated thumbnail id.
Publish thumbnail to YouTube
vidseeds_publish_thumbnail_to_youtubewhen the video is on a connected channel (seevidseeds-publishingfor connections).- Bulk YouTube limit: YouTube rate-limits custom-thumbnail uploads separately from VidSeeds.ai seeds/MCP quota. For bulk replacements, plan no more than about 100 thumbnail uploads per connected YouTube channel/account per rolling 24 hours. If YouTube returns
uploadRateLimitExceeded/ "too many thumbnails recently", stop the batch, persist the next video id, and resume later.
Thumbnail Studio (research → brief → generate)
Use when you want data-informed creative direction:
| Step | Tool |
|---|---|
| Trends in niche | vidseeds_get_thumbnail_trends |
| Niche detection | vidseeds_detect_thumbnail_niche |
| Frame analysis (from video refs) | vidseeds_analyze_thumbnail_frames, vidseeds_select_best_thumbnail_frame |
| Creative brief | vidseeds_build_thumbnail_brief |
| Subject ideas | vidseeds_suggest_thumbnail_subjects |
| Overlay copy options | vidseeds_generate_thumbnail_overlay_texts |
| Style profiles | vidseeds_get_thumbnail_style_profiles, vidseeds_save_thumbnail_style_profile |
| Visual audit / CTR sim | vidseeds_audit_thumbnail_visual, vidseeds_simulate_ctr |
| Custom upload | vidseeds_upload_custom_thumbnail |
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.
- yesterday First seen · 66 lines · 60 tokens per session scan A 6fabfa6a5987
vidseeds-thumbnails is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (935 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 898 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
viral-tech-reel-editor
End-to-end viral tech reel production for Instagram Reels and TikTok using 2026 trend grammar — retention-first pacing, punch-ins, 3D cinematic AI-generated shots, motion design graphics, proof b-roll, trending SFX, karaoke captions (Georgian/English), safe-zone layout, and QA-gated 1080x1920 export. This skill should…
prompt-translator
A tool that rewrites an existing AI video prompt from one video model's preferred format into another model's format. It uses example prompts comparing the same kinds of scenes across different models.
seedance-debugger
A troubleshooting guide for fixing common problems in Seedance 2.0 AI-generated videos, such as changing faces, unwanted text, watermarks, style changes, or broken scene transitions.
kling-prompter
A prompt-writing guide for Kling 3.0, a video-generation model. It covers short videos, story-driven videos with dialogue or sound, and animating an existing reference image.
model-selector
A guide that recommends suitable AI video-generation models based on the requested scene, length, audio, language, platform, budget, and other constraints.