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/egressgit clone --depth 1 https://github.com/openclaw/crabboxWrote 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/openclaw/crabbox/egress)<a href="https://agentmods.dev/commands/openclaw/crabbox/egress"><img src="https://agentmods.dev/badge/commands/openclaw/crabbox/egress.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 | $0.00000 | $0.01518 |
| Opus 5 | $0.00000 | $0.00759 |
| Sonnet 5 | $0.00000 | $0.00304 |
| Haiku 4.5 | $0.00000 | $0.00152 |
Grade A, and why
egress 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 4d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
egress
crabbox egress gives a lease mediated outbound network: a lease-local browser
or app proxies its traffic out through the machine running the egress host
agent, rather than reaching the internet directly from the box.
crabbox egress start --id blue-lobster --profile slack
crabbox egress start --id blue-lobster --profile slack --daemon
crabbox desktop launch --id blue-lobster --browser --url https://example.com/login --egress slack
crabbox egress status --id blue-lobster
crabbox egress stop --id blue-lobster
How it works
egress start does three things:
- Installs a short-lived egress client helper on the lease.
- Starts a loopback HTTP proxy on the box (default
127.0.0.1:3128). - Runs a local host bridge on the operator machine.
Both sides connect outbound to the coordinator using one-use tickets. The coordinator pairs the two WebSockets and forwards multiplexed proxy frames; it never opens internet connections itself. Only the host agent dials real outbound TCP connections.
Automatic egress start sends the client ticket through SSH stdin, keeping it
out of SSH, remote shell, and helper process arguments. A foreground helper
validates and closes the bounded SSH input, then hands it through a private
pipe to the detached client before returning. Invalid input fails without
starting a client or falling back to coordinator login. Manual
host/client --ticket behavior is unchanged.
The data path is:
browser/app in lease
-> lease 127.0.0.1:3128 (egress client)
-> coordinator Durable Object (pairs the two sockets)
-> local crabbox egress host process
-> internet from the operator machine
desktop launch --egress <profile> wires the lease-local proxy into the
browser by appending:
--proxy-server=http://127.0.0.1:3128
Override the proxy address with --egress-proxy if you changed --listen.
The portal lease detail page shows the active egress
session, host/client connection state, and copyable egress status /
egress stop commands. It does not expose tickets or raw proxy URLs.
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.
- 4d ago First seen · 163 lines · 0 tokens per session scan A a80d1fc86f5e
egress is a command published in the GitHub repository openclaw/crabbox (1,362 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,518 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
git
Git operations with intelligent commit messages and workflow optimization.
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.