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/artifactsgit 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 | $0.03473 |
| Opus 5 | $0.00000 | $0.01736 |
| Sonnet 5 | $0.00000 | $0.00695 |
| Haiku 4.5 | $0.00000 | $0.00347 |
Grade A, and why
artifacts 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
artifacts
crabbox artifacts turns a desktop lease into durable QA evidence: it collects
screenshots, video, logs, doctor output, and metadata into a bundle, makes
trimmed review media, writes QA summary markdown, and publishes inline-ready
assets to a pull request.
Reach for it when a desktop/WebVNC issue or UI fix needs more than a one-off screenshot. Subcommands:
collect— gather a full evidence bundle into a directory.video— record an MP4 from a desktop lease.gif— make a trimmed GIF from a recorded video (alias forcrabbox media preview).template— write QA summary markdown.publish— upload a bundle and optionally comment on a PR.list/pull— read or download files from a published manifest.
Collect
crabbox artifacts collect --id blue-lobster --output artifacts/blue-lobster
crabbox artifacts collect --id blue-lobster --all --duration 20s --output artifacts/blue-lobster
crabbox artifacts collect --id blue-lobster --run run_123 --output artifacts/blue-lobster
By default collect writes:
metadata.jsonscreenshot.pngdoctor.txtwebvnc-status.jsonwhen a coordinator login is configuredlogs.txtandrun.jsonwhen--run <run-id>is provided
The default bundle directory is private. An explicit --output directory keeps
its existing sharing permissions, while retained logs.txt and run.json
remain owner-only. Publishing is unchanged.
--all enables --video and --gif, so the bundle also records screen.mp4,
writes a screen.contact.png contact sheet, and produces a trimmed
screen.trimmed.gif. --gif requires --video (or --all). Linux video uses
remote ffmpeg/X11 capture; native Windows captures frames in the interactive
console session and encodes the MP4 locally with ffmpeg. MP4 capture is
supported for Linux and native Windows desktop targets only.
When the output directory is omitted, Crabbox derives one from the lease ID and slug. The bundle is not collected for static (BYO) hosts on non-Linux targets, or for the Blacksmith provider, which owns its own connectivity.
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 · 374 lines · 0 tokens per session scan A 0a935892fc66
artifacts 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 3,473 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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.