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 agentmods add skills/grayhatdevelopers/vidxp/vidxp-installnpx skills add grayhatdevelopers/vidxp --skill vidxp-installgit clone --depth 1 https://github.com/grayhatdevelopers/vidxpWhat 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 | $0.00078 | $0.01166 |
| Opus 5 | $0.00039 | $0.00583 |
| Sonnet 5 | $0.00016 | $0.00233 |
| Haiku 4.5 | $0.00008 | $0.00117 |
Grade A, and why
vidxp-install 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 2d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install VidXP
Reuse a working local VidXP setup when the user approves it. Otherwise, help them choose a setup, install only what they approve, verify it, and connect Codex to its local MCP server.
Check for an existing installation first
Before offering a new install, look for every vidxp executable available to the local shell. Do not modify any candidate. For each one, run:
<absolute-vidxp-path> --version
<absolute-vidxp-path> desktop-probe --json --desktop-version codex-plugin --request-id codex-install
For each successful probe, show the user its executable, version, data_root, repository_root, and model_root. These are the installation's effective paths; existing downloaded models under the reported model_root can be reused. Ask the user to confirm whether to reuse that installation and those paths.
If the user approves reuse, skip installation and upgrades. Use executables from that same environment, preserve the reported paths when registering MCP, and repair a missing surface or dependency only with approval. If no compatible installation is found or the user declines reuse, continue with the setup choice.
Start with the choice
Determine which surface the user wants before downloading anything:
- Recommend Desktop when they want a guided installer, managed runtime, feature selection, or browser interface.
- Recommend CLI when they want scripting, terminal control, automation, or a minimal agent-only setup.
- Clarify that both keep video processing local. The plugin itself is only the bootstrap and agent guidance; VidXP provides the actual MCP server after installation.
- A browser-only ChatGPT session cannot install native software. Continue only when the agent has an authorized local shell, or give the user the exact manual steps.
Ask before starting an installer, changing a tool environment, or downloading models. Do not download model weights until the user has chosen the search capabilities that need them.
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.
- 2d ago First seen · 89 lines · 78 tokens per session scan A ee855a2ce116
vidxp-install is a skill published in the GitHub repository grayhatdevelopers/vidxp (30 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 1,166 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
native-subtitle-quote-image
将本地视频或用户有权处理的在线视频，经过来源获取、文字稿定位、选题选句、精确取帧、紧凑裁切、3:4 拼图和逐张质检，制作成视频字幕社交长图。支持两种明确分开的输出：保留画面内已烧录字幕的原生字幕模式，以及把已审核的时间点与台词绘制到真实视频帧上的脚本字幕模式。用户要求原生字幕截图、字幕帧拼图、YouTube 金句长图、台词截图、不重绘字幕、自定义中文台词，或调整主图比例、字幕区域、台词间隔和美感时使用。.
authoring-video-templates
Use when creating or editing a video template JSON (the template descriptor), adding or changing sections/filters/maps/variables/transitions/looks/motion/audio/layers, or debugging template validation errors in ffmpeg-video-composer.
reflectworld-percept
Perception automatically analyzes video segments from Eye using cloud VLM (Gemini). Working Memory tracks cross-segment event context. Results flow to ReflectWorld (storage) and Act (rules) via PostProcessor — all automatic.
reflectworld
You have access to ReflectWorld, a visual perception and persistent memory system. It gives you eyes and memory for cameras.
reflectworld-mem
Search and manage ReflectWorld video memories from ReflectWorld cameras.
core-architecture-patterns
Use when adding a segment type, platform adapter, editor manager, core service, or descriptor effect (look/grade/motion/section-audio field) in packages/ffmpeg-video-composer, or when wiring new dependencies into the tsyringe container.