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 commands/bybren-llc/safe-agentic-workflow/media-extract-framesgit clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflowWrote 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/commands/bybren-llc/safe-agentic-workflow/media-extract-frames)<a href="https://agentmods.dev/commands/bybren-llc/safe-agentic-workflow/media-extract-frames"><img src="https://agentmods.dev/badge/commands/bybren-llc/safe-agentic-workflow/media-extract-frames.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00600 |
| Opus 5 | $0.00009 | $0.00300 |
| Sonnet 5 | $0.00004 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
media-extract-frames 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 yesterday.
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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/media:extract-frames
Read the name carefully before reaching for this one. It extracts no images. It finds the moments that matter in a video and writes them up as a storyboard, for edit decision support.
Overview
Gemini-only. Selects key frames on visual significance rather than fixed intervals, then describes each in text. NAMING DRIFT: nothing is written to disk — there is no ffmpeg call, no image write and no output path anywhere in the source, so "extract" means "describe" here. If you need scene boundaries instead, use /media:scene-detect.
Invocation
/media:extract-frames <path>— default--storyboard.--detailedor--json— prose or machine-readable variants.--max N— caps the frame count; the default is 20 key frames.- Preconditions: Gemini 3+ for video; MP4, MOV, AVI, MKV or WEBM; up to 100MB.
What It Does
- Verifies the target with a pre-executed
!{file {{args}} 2>/dev/null || echo "File not found"}— the stderr redirect is what makes the echo branch the observable failure path. - Identifies key frames on five signals: scene changes, significant moments (key actions, reactions, events), composition shifts, text appearances (title cards, lower thirds, captions), and subject changes.
- Per frame, records a precise timestamp, a detailed visual description, subjects and objects, composition and framing notes, and narrative relevance.
- Renders either the markdown Key Frame Report or the Storyboard table with columns for number, timestamp, visual, action, and audio or dialogue.
- Sends video contents to the Gemini API — stated as an explicit privacy note.
Provider Parity
- Gemini — the only implementation. No
.claude/commandscounterpart, so zero Claude parity. - Frame selection is significance-based and the source states the count varies by content complexity, so two runs over the same input are not guaranteed to agree.
Citations
- Gemini CLI Authoring Guide — the TOML command format and multimodal conventions this file follows.
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.
- yesterday First seen · 57 lines · 18 tokens per session scan A 9de3f19deb2f
media-extract-frames is a command published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 600 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
help
Category: System Syntax: /help [command|topic].
translate-docs
翻译项目文档到指定语言.
ship
Deploy feature through automated staging validation to production with rollback testing.
review-tasks
审查任务的忠实度、可执行性、依赖关系与验证.
clarify
Reduce spec ambiguity via targeted questions with adaptive auto-invocation (planning is 80% of success).
help
Analyze workflow state and provide context-aware guidance with visual progress indicators and recommended next steps.