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 ai-ecoverse/slicc --skill ffmpeggit clone --depth 1 https://github.com/ai-ecoverse/sliccWrote 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/ai-ecoverse/slicc/ffmpeg)<a href="https://agentmods.dev/skills/ai-ecoverse/slicc/ffmpeg"><img src="https://agentmods.dev/badge/skills/ai-ecoverse/slicc/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/skills/ai-ecoverse/slicc/ffmpeg"><img src="https://agentmods.dev/badge/skills/ai-ecoverse/slicc/ffmpeg.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 | $0.00079 | $0.01265 |
| Opus 5.5 | $0.00032 | $0.00506 |
| Sonnet 5.5 | $0.00016 | $0.00253 |
| Haiku 4.5 | $0.00008 | $0.00127 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ffmpeg / ffprobe
Both commands have two engines behind one CLI:
- mediabunny (WebCodecs, hardware encoders, streams from disk): used
automatically for one-input → one-output jobs whose every option it can
express — remux, transcode to h264/hevc/vp8/vp9/av1 + aac/opus/mp3/vorbis/
flac/pcm,
-ss/-t/-totrims,-vf crop,scale,fps(written in that order;transposeonly on its own),-ac/-ar,-b:v/-b:a/-crf,-movflags +faststart,-metadata. Needs no install. An explicit encoder always re-encodes;-c copynever does.ffprobeanswers from its container index (typed fields, no wasm boot). @ffmpeg/corewasm (ipk-installed): everything else — lavfi sources,-f concat, filtergraphs (drawtext,overlay,loudnorm, …), analysis sinks (-f null), image/GIF output, codecs the browser lacks.
The choice is automatic and stderr says which engine ran. Force one with
FFMPEG_ENGINE=wasm ffmpeg … (byte-identical ffmpeg behaviour) or
FFMPEG_ENGINE=mediabunny ffmpeg … (fail instead of falling back, and see
why). Without an explicit -c, mediabunny copies streams the container can
hold rather than re-encoding them.
There is no separate ffprobe binary: on the wasm engine ffprobe runs
ffmpeg -hide_banner -i <file> with no output and parses the Input #N
banner. Unsupported options are rejected by name (never silently dropped).
Install (wasm engine only)
ipk add -g @ffmpeg/[email protected]
Prefer -g so scoops and the cone share one copy. Follow the pinned
version printed by ffmpeg --help / ffprobe --help if it differs.
There is no CDN fallback. ffmpeg -version prints a core: line saying
which core is loaded.
Multi-threaded core (opt-in, single-input jobs only). On a cross-origin-isolated leader (the hosted tab on current Chrome):
ipk add -g @ffmpeg/[email protected]
FFMPEG_CORE=mt ffmpeg -i in.mp4 -c:v libx264 out.mp4
It uses several CPU cores for libx264 / libvpx and caps -threads and
-filter_threads for you (pass your own to override). It deadlocks on any
job with more than one input (ffmpeg's per-input demux threads), so such
jobs are refused on it — run them without FFMPEG_CORE=mt. The first
ffmpeg in a session decides which core stays loaded.
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 · 110 lines · 79 tokens per session scan A 8da7c018c238
ffmpeg is a skill published in the GitHub repository ai-ecoverse/slicc (34 stars, last pushed 2d ago), licensed Apache-2.0. It adds 79 tokens to every session and 1,265 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 2026-09-05.
Other skills, from other repositories
browse
Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch/search, diagnostics, and Browse.sh skill discovery/installation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase…
moli-webfetch
Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…
pinchtab-stealth-score
Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, rebrowser, deviceandbrowserinfo, iphey, whoer, browserscan, pixelscan, fingerprint-scan, incolumitas, fvision, amiunique, browserleaks, creepjs, coveryourtracks, fingerprint-demo). Starts a Docker PinchTab container per…
actionbook-scraper
Generate and verify web scraper scripts using Actionbook's verified selectors. Auto-validates generated scripts and fixes errors.
wttr-weather
Weather via wttr.in GET (no key). Use for weather/forecast; prefer os.http.request.
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.