sandbox-start

sandbox-start is a command for coding agents from proticom/gnosys. It costs 0 tokens per session (352 once invoked), scanned A, original, MIT.

A command that starts Gnosys's background sandbox process, which lets an agent access memory operations. It waits until the process is ready and reports its process ID.

In plain words
What is it for?
Use it to start the sandbox, choose a database directory, or receive the result as JSON for scripts.
Why use it?
It removes the need to start the memory service manually before using it. It can reuse a sandbox that is already running.

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/proticom/gnosys/sandbox-start
Clone the repo
git clone --depth 1 https://github.com/proticom/gnosys

Wrote 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.

agentmods badge for sandbox-start

README.md
[![agentmods](https://agentmods.dev/badge/commands/proticom/gnosys/sandbox-start.svg)](https://agentmods.dev/commands/proticom/gnosys/sandbox-start)
Your own site
<a href="https://agentmods.dev/commands/proticom/gnosys/sandbox-start"><img src="https://agentmods.dev/badge/commands/proticom/gnosys/sandbox-start.svg" alt="Measured on agentmods" height="20"></a>
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 352 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 $0.00352
Opus 5 $0.00000 $0.00176
Sonnet 5 $0.00000 $0.00070
Haiku 4.5 $0.00000 $0.00035

Measured 3d ago against content hash d19f905db4dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sandbox-start 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 3d 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/sandbox-start.md · 68 lines

What it actually says

gnosys sandbox start

Start the Gnosys sandbox background process for low-latency agent access to memory operations.

Usage

gnosys sandbox start
gnosys sandbox start --db-path /path/to/db
gnosys sandbox start --persistent --json

Options

Option Description
--persistent Keep running across reboots (reserved/future use)
--db-path <path> Custom database directory for the sandbox server
--json Output result as JSON

Behavior

  1. Calls startSandbox({ persistent, dbPath, wait: true }).
  2. Reuses an already-running sandbox when possible.
  3. Waits for readiness, then prints the process ID.

Human output

Gnosys sandbox running (pid: 12345)

JSON output

Success:

{
  "ok": true,
  "pid": 12345
}

Failure:

{
  "ok": false,
  "error": "error message"
}

On failure without --json, prints Failed to start sandbox: ... to stderr and exits with code 1.

Validation

cd gnosys-public
npm run cli -- sandbox start --help
npx vitest run src/test/sandbox-start-command-handler.test.ts
  • gnosys sandbox stop — stop the background process.
  • gnosys sandbox status — check whether the sandbox is running.
  • gnosys helper generate — generate the agent helper library for sandbox access.
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. 3d ago First seen · 68 lines · 0 tokens per session scan A d19f905db4dc

Subscribe to this mod's changes

sandbox-start is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 352 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 2026-08-31.