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 wangxin6x/AutoVideo-Agent --skill auto-videogit clone --depth 1 https://github.com/wangxin6x/AutoVideo-AgentWrote 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/wangxin6x/autovideo-agent/auto-video)<a href="https://agentmods.dev/skills/wangxin6x/autovideo-agent/auto-video"><img src="https://agentmods.dev/badge/skills/wangxin6x/autovideo-agent/auto-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/wangxin6x/autovideo-agent/auto-video"><img src="https://agentmods.dev/badge/skills/wangxin6x/autovideo-agent/auto-video.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 | $0.00086 | $0.00478 |
| Opus 5.5 | $0.00034 | $0.00191 |
| Sonnet 5.5 | $0.00017 | $0.00096 |
| Haiku 4.5 | $0.00009 | $0.00048 |
Grade A, and why
auto-video 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 1mo 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.
What it actually says
AutoVideo Pipeline
Use this skill to operate the AutoVideo-Agent repository honestly and reproducibly.
Workflow
- Read AGENTS.md and inspect the target Markdown script before running anything.
- Confirm the script has a top-level '#' title and one or more '##' scene headings. Scene fields may include duration, visual, and narration.
- Run autovideo run <script.md> for v0.1-compatible offline mode, or add --config <config.yaml> for provider mode. Use --output when the build must be isolated.
- Inspect the JSON printed by the CLI and then read /report.json and /manifest.json.
- Run autovideo qa . Treat PASS as validated, WARNING as usable with declared limitations, and FAIL as incomplete.
- When changing core behavior, run python -m pytest and git diff --check before reporting completion.
Mode Boundaries
Without --config, preserve the v0.1 deterministic placeholder PPM cards, silent WAV, manifest, report, and FFmpeg degradation behavior. With a v0.2 config, select placeholder or ComfyUI media plus Mock or Command TTS; generate scene-level SRT from actual audio duration, a contiguous timeline, H.264/AAC MP4, and deterministic QA. Do not claim MiniMax, OpenAI TTS, Volcengine, ElevenLabs, word-level alignment, or generic real-media adapters are implemented.
Agent Request Example
For a request such as:
Turn examples/demo-script.md into a video and run QA.
execute the CLI, run autovideo qa on the build directory, verify the report and manifest, and summarize the actual status, output paths, duration, scene count, provider names, and warnings. Do not infer media quality from prompt text or claim a remote provider was tested when only HTTP mocks ran.
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.
- 1mo ago First seen · 30 lines · 86 tokens per session scan A 2f8688f991d0
auto-video is a skill published in the GitHub repository wangxin6x/AutoVideo-Agent (90 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 478 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 2026-08-30.
Other skills, from other repositories
lanshu-create-ai-presenter-video
Turn a topic or finished script into a complete, publish-ready explainer video — led by an AI presenter from an authorized adult presenter image, or performed with no presenter in one of twelve explainer styles (nine visual styles and three narrative ones). Not for promos, ads, or footage montages. Use for new…
codex-autoresearch
Run repeated, measured Git experiments toward a numeric target; keep improvements and revert failures. Use for autonomous optimization or managing an autoresearch run, not one-shot edits.
seedance-2-5-video-director
Design, derive, optimize, diagnose, and rewrite scripts or copy-ready prompts specifically for Dreamina/即梦 Seedance 2.5. Use for new text/image/video/audio-to-video concepts, exact-timeline videos, 30-180-second Long Video, extension, video editing, Clay Renderer, seamless transitions, multi-grid storyboards…
novel-writing
Use when setting up a fiction project, planning, drafting, revising, or reviewing fiction where chapter versions, author feedback, character knowledge, scene causality, dialogue, or style fidelity matter.
script-to-shootable-storyboard
A guide for turning scripts, story outlines, dialogue, or existing storyboards into detailed shot plans. A storyboard is a sequence of planned camera shots showing what viewers see and hear.
goal-prompt-builder
Build high-quality /goal commands for OpenAI Codex CLI 0.128+ that maximize audit-friendliness and minimize false-completion. Use this skill whenever the user wants to write, draft, generate, improve, or refine a /goal prompt — even if they don't say "skill" — including phrases like "help me write a goal", "design a…