config

A command for inspecting and updating Crabbox settings. Crabbox is a tool that manages machines or development environments, and this command handles its configuration file, broker connection, and related options.

In plain words
What is it for?
Use it to print the configuration path, view merged settings as text or JSON, or configure the broker URL, provider, operating mode, and web-based access options.
Why use it?
It avoids manually finding or editing configuration files and shows the effective settings with secrets hidden. It also provides a controlled way to set the broker URL and provider mode.

Command

Install

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.

agentmods
npx agentmods add commands/openclaw/crabbox/config
Clone the repo
git clone --depth 1 https://github.com/openclaw/crabbox
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,167 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02167
Opus 5 $0.00000 $0.01084
Sonnet 5 $0.00000 $0.00433
Haiku 4.5 $0.00000 $0.00217

Measured 2d ago against content hash 639fc9417217, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

config 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.

docs/commands/config.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

config

crabbox config inspects and updates user configuration. It has three subcommands:

crabbox config path
crabbox config show [--json]
crabbox config set-broker --url <url> [--provider <provider>] [--mode managed|registered] [--auto-webvnc=false] [--token-stdin] [--admin-token-stdin]

config path

Prints the selected user config path:

crabbox config path

The file lives at <os-user-config-dir>/crabbox/config.yaml (for example ~/.config/crabbox/config.yaml on Linux or ~/Library/Application Support/crabbox/config.yaml on macOS). Set CRABBOX_CONFIG to point at a different file; that override is used for both reads and writes. config path and the config= header from config show report that override exactly as supplied, including a relative or symlink path. Without an override, they report the absolute OS user-config path. Reporting a path does not create the file or change its trust classification.

config show

Prints the merged effective configuration with secret values redacted:

crabbox config show
crabbox config show --json

The merge combines, in order: the user config file, then any repo-local crabbox.yaml or .crabbox.yaml found in the current directory (a repo file overrides user defaults for that checkout), then environment variables. When CRABBOX_CONFIG is set, only that file is read (the repo-local files are skipped). This changes selection only: an explicit path inside the active repository, or a symlink that resolves into it, still has repository trust. config show reflects the resulting effective values, including provider defaults applied at load time; per-command flags are not part of what it reports. The provider line includes provider_selected and provider_source (JSON: providerSelected and providerSource). With only compatibility metadata, the public provider value is the empty string and the state is provider_selected=false provider_source=compiled_default; it is not an actionable provider selection. The public top-level serverType / text type is also empty in that state so provider-specific compatibility defaults are not presented as effective; provider-specific configuration sections remain visible. Selections in user_config, repo_config, or the environment retain the canonical provider name and report selected=true. Passing config show --provider <name> reports flag because that command-scoped override wins the merge.

Read the full file on GitHub · 216 lines

Changes

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.

  1. 2d ago First seen · 216 lines · 0 tokens per session scan A 639fc9417217

Subscribe to this mod's changes

config 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 2,167 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.