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 glifxyz/glif-mcp-server --skill audio-and-videogit clone --depth 1 https://github.com/glifxyz/glif-mcp-serverWrote 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/glifxyz/glif-mcp-server/audio-and-video)<a href="https://agentmods.dev/skills/glifxyz/glif-mcp-server/audio-and-video"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/audio-and-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/glifxyz/glif-mcp-server/audio-and-video"><img src="https://agentmods.dev/badge/skills/glifxyz/glif-mcp-server/audio-and-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 | $0.00225 | $0.01517 |
| Opus 5.5 | $0.00090 | $0.00607 |
| Sonnet 5.5 | $0.00045 | $0.00303 |
| Haiku 4.5 | $0.00022 | $0.00152 |
Grade A, and why
audio-and-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 7d 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 -fsSL "<media url>" -o public/audio/click.mp3 How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route audio and video work to Glif. Glif picks the models; you write a clear brief and handle the files. The user's explicit instructions come first, within host safety rules.
1. Write the brief
Describe the result, not the model. Include what matters:
- Voice: the exact script in quotes, language, voice (age, accent, energy), pace, and emotion cues like a whisper, a laugh or a sigh at the right words. Glif can play voice samples to pick from. Clone a voice only from a sample whose owner agreed.
- Music: mood, genre, tempo, length, and vocals with lyrics or instrumental. Say if it must loop or sit under a voice (Glif can duck it).
- Sound effects and UI sounds: what triggers each one, length (UI sounds under 1 second) and how subtle. Ask for a matched set when there are several. For a video, Glif can add foley synced to the action.
- Ambience: the place and a seamless loop length.
- Video: write it in shots. For each shot: camera and framing first, then the action with clear motion verbs, the light source and the look (film stock, style). Add length, aspect ratio (16:9, 9:16, 1:1 or 4:5) and whether it needs sound. For tight control, ask for stills first, then animate the approved ones.
- People on screen: UGC-style creators, talking avatars, lipsync and dubbing. Use real people's faces or voices only with their consent. No fake testimonials or invented claims, and label synthetic creators where the platform requires it.
- Edits: attach the source files and say exactly what changes and what stays: captions (word-highlight, animated, styled), punch zooms, background swap, trims and joins, stem separation, noise cleanup.
2. Starting from a reference
When the user supplies or picks a file to build on, say what the reference provides and what is new:
- Image to video: subject motion, camera move, length and framing. "One continuous shot, no cuts" helps for orbits and bullet time.
- Product photo to ad: keep the product identical; only the camera, light and setting move.
- Song or voice to video: which parts are sung or spoken, the look, and where lipsync is needed.
- Driving video: which character takes over the motion, and what stays from the original (camera, timing, sound).
- Room photo: the style to stage or renovate in, and whether to add a walkthrough video.
- Reference video for structure: copy its pacing, shot order and hook only. Never copy its people, footage, logos or brand.
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.
- 7d ago Changed · +21 lines · +14 tokens per session eab6cc5c6c1b
- 8d ago First seen · 49 lines · 211 tokens per session scan A efd9607ae882
audio-and-video is a skill published in the GitHub repository glifxyz/glif-mcp-server (215 stars, last pushed 7d ago), licensed MIT. It adds 225 tokens to every session and 1,517 once invoked, about $0.0009 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 2026-10-08.
Other skills, from other repositories
n8n-agents
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain. AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output…
n8n-subworkflows
Build reusable, composable n8n sub-workflows. Use when extracting shared logic, building anything multi-step or reused across workflows, or any workflow over 10 nodes — and whenever the user mentions sub-workflows, Execute Workflow, reuse, shared/common logic, modular workflows, "Define Below" inputs…
n8n-validation-expert
Interpret validation errors and guide fixing them. Use when encountering validation errors, validation warnings, false positives, operator structure issues, or need help understanding validation results. Also use when asking about validation profiles, error types, the validation loop process, or auto-fix capabilities.…
n8n-workflow-patterns
Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, batch processing, or scheduled…
n8n-binary-and-data
Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user mentions $binary, binaryPropertyName, "read the PDF", "attach the file", "send…
n8n-code-tool
Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the query input, returning a string result, defining an input schema…