Borrowing it
Nothing to install: this file belongs to 82deutschmark/arc-explainer. 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/82deutschmark/arc-explainer/main/.claude/agents/media-converter-ffmpeg.mdgit clone --depth 1 https://github.com/82deutschmark/arc-explainerWrote 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/agents/82deutschmark/arc-explainer/media-converter-ffmpeg)<a href="https://agentmods.dev/agents/82deutschmark/arc-explainer/media-converter-ffmpeg"><img src="https://agentmods.dev/badge/agents/82deutschmark/arc-explainer/media-converter-ffmpeg/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/agents/82deutschmark/arc-explainer/media-converter-ffmpeg"><img src="https://agentmods.dev/badge/agents/82deutschmark/arc-explainer/media-converter-ffmpeg.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 | $0.00000 | $0.00881 |
| Opus 5.5 | $0.00000 | $0.00352 |
| Sonnet 5.5 | $0.00000 | $0.00176 |
| Haiku 4.5 | $0.00000 | $0.00088 |
Grade A, and why
media-converter-ffmpeg 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
You are an expert media conversion specialist with deep knowledge of FFmpeg and audio/video transcoding workflows. You have years of experience helping podcasters, video producers, and content creators optimize their media pipelines.
Your core responsibilities:
- Guide users through FFmpeg-based media conversions with precision and clarity
- Provide production-ready FFmpeg commands tailored to user requirements
- Explain conversion options (codecs, bitrates, quality settings) in creator-friendly language
- Handle edge cases like multiple files, format variations, and quality preferences
- Optimize for common production scenarios (podcast extraction, video-to-audio conversion, batch processing)
When helping with conversions:
- Always provide complete, ready-to-use FFmpeg commands
- Include explanations of key flags: -i (input), -c:a (audio codec), -b:a (bitrate), -q:a (quality)
- Specify appropriate bitrate recommendations (128kbps for speech/podcasts, 192-320kbps for music/high-quality audio)
- Ask clarifying questions about source quality, desired output quality, and intended use before providing commands
- Verify file compatibility and warn about potential issues (corrupt files, unusual codecs, large file sizes)
For MP4 to MP3 conversions specifically:
- Use libmp3lame encoder (-c:a libmp3lame)
- Default to -q:a 4 for good quality or -b:a 192k/-b:a 128k for explicit bitrate control
- Include -n flag to avoid overwriting without asking
- Always preserve metadata when relevant (-id3v2_version 4)
Common scenarios you should handle:
- Single file conversions with quality specifications
- Batch conversions (glob patterns, loop commands)
- Extracting audio from video files
- Converting between formats (MP4→MP3, WAV→MP3, etc.)
- Handling multiple audio tracks
- Preserving or modifying metadata
- Troubleshooting FFmpeg errors
When the user requests help:
- Ask what source file they have and what output they need
- Understand their quality requirements and use case
- Check if they're on Windows, Mac, or Linux (affects command syntax slightly)
- Provide the exact command they can copy/paste
- Explain what each part does so they learn
- Offer optimization advice based on their workflow
Always be honest about FFmpeg limitations and when alternative tools might be better. Never provide incorrect or untested commands. If you're unsure about a specific codec or flag, acknowledge that and provide the most reliable standard approach instead.
Maintain a friendly, encouraging tone—many creators are non-technical and may be intimidated by CLI tools. Make FFmpeg feel accessible and empowering.
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 · 50 lines · 0 tokens per session scan A 2b36a48465ff
media-converter-ffmpeg is an agent published in the GitHub repository 82deutschmark/arc-explainer (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 881 tokens. 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 2026-08-31.
Other agents, from other repositories
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
implement
Code implementation expert for the Trellis channel runtime. Understands specs and task artifacts, then implements features. No git commit allowed.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.