Borrowing it
Nothing to install: this file belongs to quangdang46/openproxy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/quangdang46/openproxy/main/.agents/skills/openproxy-video/SKILL.mdgit clone --depth 1 https://github.com/quangdang46/openproxyWrote 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/quangdang46/openproxy/openproxy-video)<a href="https://agentmods.dev/skills/quangdang46/openproxy/openproxy-video"><img src="https://agentmods.dev/badge/skills/quangdang46/openproxy/openproxy-video/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/quangdang46/openproxy/openproxy-video"><img src="https://agentmods.dev/badge/skills/quangdang46/openproxy/openproxy-video.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 | $0.00112 | $0.05559 |
| Opus 5.5 | $0.00045 | $0.02224 |
| Sonnet 5.5 | $0.00022 | $0.01112 |
| Haiku 4.5 | $0.00011 | $0.00556 |
Grade A, and why
openproxy-video scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS "$OPENPROXY_URL/v1/videos/anything" \ How it starts
The opening of the file, as written. The whole thing — 351 lines — stays where its author put it; the contents beside it link to each section on GitHub.
openproxy-video — async video generation
Video is the only OpenProxy endpoint family that is two-phase. POST /v1/videos/generations returns a job id in ~1 second; the MP4 does not exist yet. You must GET /v1/videos/{id} until the job reaches a terminal state, then fetch the file from the URL in the finished payload. Treating the create response as the video is the single most common mistake.
Video routes live in src/server/api/media.rs and are registered in src/server/api/mod.rs:220-261.
0 · The five routes that exist
| Method | Path | Handler | Notes |
|---|---|---|---|
POST |
/v1/videos/generations |
media::video_generations |
Text-to-video and image-to-video. |
POST |
/v1/videos/edits |
media::video_edits |
xAI Grok Imagine. Multipart-capable. |
POST |
/v1/videos/extensions |
media::video_extensions |
xAI Grok Imagine. Multipart-capable. |
GET |
/v1/videos/{id} |
media::video_get |
Poll. Not a download route. |
POST |
/v1/video/generations |
media::video_generations |
Legacy singular spelling, kept for older clients. |
Each is also registered under a doubled prefix — /v1/v1/videos/generations, /v1/v1/videos/edits, /v1/v1/videos/extensions, /v1/v1/videos/{id}, /v1/v1/video/generations — so a client that already appends /v1 to its base URL still resolves. There is no GET /v1/videos list route and no content-download route. To get the bytes, read the URL out of the finished poll payload and download it yourself.
All five accept OPTIONS preflight.
1 · Which providers actually serve video
Exactly three, enforced by video_provider_supported (src/server/api/media.rs:2408):
| Provider key | Adapter | Upstream | Catalog models (kind: "video") |
|---|---|---|---|
xai |
native (default shape) | https://api.x.ai/v1/videos/{action} |
grok-imagine-video |
openrouter |
collection-root POST | https://openrouter.ai/api/v1/videos |
none built in — add a custom model |
vertex |
translated to predictLongRunning |
https://aiplatform.googleapis.com |
veo-3.1-generate-preview, veo-3.1-fast-generate-preview, veo-3.0-generate-001, veo-2.0-generate-001 |
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.
- 29d ago First seen · 351 lines · 112 tokens per session scan A 3afd98dbfe77
openproxy-video is a skill published in the GitHub repository quangdang46/openproxy (29 stars, last pushed 5d ago), licensed MIT. It adds 112 tokens to every session and 5,559 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-29.
Other skills, from other repositories
implementing-api-schema-validation-security
Implement API schema validation using OpenAPI specifications and JSON Schema to enforce input/output contracts and prevent injection, data exposure, and mass assignment attacks.
keirouter-chat
Chat / code generation via KeiRouter using OpenAI /v1/chat/completions or Anthropic /v1/messages format with streaming + auto-fallback combos. Use when the user wants to ask an LLM, generate code, summarize text, or run prompts through KeiRouter.
keirouter-embeddings
Generate vector embeddings via KeiRouter /v1/embeddings using OpenAI / Mistral / Cohere / Voyage / NVIDIA / AWS Bedrock and other embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
10router
Entry point for 10Router — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions 10Router, TENROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant capability…
post-processing
Extract, analyze, and summarize simulation output data — pull spatial fields at specific timesteps, compute time-series trends and detect steady state, extract line profiles through the domain, generate statistical summaries and distributions, calculate derived quantities (gradients, fluxes, volume fractions…
linear-solvers
Select and configure linear solvers for Ax=b systems arising in numerical simulations — choose between direct (LU, Cholesky) and iterative (CG, GMRES, BiCGSTAB, MINRES) methods, analyze sparsity patterns and matrix conditioning, recommend preconditioners (AMG, ILU, IC), apply row/column scaling, and diagnose…