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/openclaw/crabbox/mediagit clone --depth 1 https://github.com/openclaw/crabboxWhat 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 | $0.00000 | $0.00944 |
| Opus 5 | $0.00000 | $0.00472 |
| Sonnet 5 | $0.00000 | $0.00189 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
media 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
media
crabbox media turns a recorded desktop video into lightweight review
artifacts. It runs entirely on your machine, needs no lease or broker, and
depends only on ffmpeg and ffprobe being on your PATH.
The command pairs naturally with desktop record and
artifacts video, which produce the MP4 source you feed in
here.
media preview
crabbox media preview converts an MP4 (or any ffmpeg-readable video) into a
small animated GIF that GitHub renders inline in issues, pull request bodies,
and comments. It can optionally also emit a trimmed MP4 clip covering the same
window.
crabbox media preview \
--input desktop.mp4 \
--output desktop-preview.gif \
--trimmed-video-output desktop-change.mp4
Both --input and --output are required.
Motion trimming
By default the preview is motion-focused so the GIF shows the change, not the idle desktop around it:
- ffmpeg
freezedetectlocates every static region across the recording. - Crabbox removes long static spans, keeps
--trim-padding(default750ms) around each moving segment, then stitches the segments together. - The stitched preview is widened to at least
--min-duration(default1500ms) when the detected motion is shorter. - If no motion is detected at all, Crabbox keeps the full source rather than emitting an empty preview.
Disable trimming and render the whole video with --no-trim-static.
Encoding
The GIF is palette-optimized for quality: ffmpeg generates a diff-mode palette,
then renders at --fps (default 24) and --width (default 1000 px) with
Lanczos scaling and Floyd–Steinberg dithering.
When gifsicle is on PATH, Crabbox runs a second optimization pass
(gifsicle -O3 --lossy=<n> --gamma=<n>) to shrink the file while preserving the
higher-quality palette. Control this with --gifsicle:
auto(default) — optimize ifgifsicleis available, otherwise skip.off— never run gifsicle.required— fail the command ifgifsicleis missing.
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 · 102 lines · 0 tokens per session scan A c4151d6c1fc6
media is a command published in the GitHub repository openclaw/crabbox (1,343 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 944 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.