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-projectsgit 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-projects)<a href="https://agentmods.dev/skills/hashgraph-online/awesome-codex-plugins/vidseeds-projects"><img src="https://agentmods.dev/badge/skills/hashgraph-online/awesome-codex-plugins/vidseeds-projects.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 | $0.00047 | $0.00941 |
| Opus 5 | $0.00023 | $0.00470 |
| Sonnet 5 | $0.00009 | $0.00188 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
vidseeds-projects 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Projects (MCP)
A project is the workspace for one video across YouTube, TikTok, Instagram, Facebook, LinkedIn, and X.
Discover projects
vidseeds_list_projects- browse with limits/filters per tool schema.vidseeds_get_project- single project record.vidseeds_get_project_snapshot- project + platform config in one call (prefer over many gets).
Create from YouTube
vidseeds_create_project_from_youtubewith the YouTube video id/URL (see tool inputs).- If metadata generation is async, poll
vidseeds_get_create_project_metadata_jobuntilcompleted. - Confirm with
vidseeds_get_project_snapshot.
Regenerate platform metadata
Re-runs optimized titles/descriptions/tags per platform from the stored transcript.
| Mode | Tool | Notes |
|---|---|---|
| Fast / small | vidseeds_regenerate_project_metadata |
Can exceed ~100s edge timeout on large projects |
| Production | vidseeds_regenerate_project_metadata_async |
Returns jobId immediately |
| Poll | vidseeds_get_regenerate_project_metadata_job |
Same result shape as sync when done |
Pass focus: "titles" (with regenerate) to use the lightweight titles-only generator (still 1 seed, but far less AI work than full variants).
Voice: If the user has multiple YouTube channels, pass channelId (UC…). With one connection, omit for auto-resolve. voiceBlendRatio optional (tool default documented in tools/list).
Reuse the same requestId on transport retries to avoid double seed charges when the tool allows it.
Keep create, regenerate, and targeted field-refresh calls for the same video close together when possible. VidSeeds.ai reuses recent per-video analysis context for about an hour during a metadata workflow, so follow-up quality checks and regenerations are usually cheaper and faster when they stay in the same project flow.
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 · 72 lines · 47 tokens per session scan A 6df99a774503
vidseeds-projects is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (935 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 941 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 2026-09-05.
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.