sandbox-test

A guided set of tests for Straddle, a payment platform, using its safe sandbox environment instead of live payments.

In plain words
What is it for?
Use it to run documented sandbox cases, test payment outcomes, diagnose unexpected statuses, and avoid duplicate test requests.
Why use it?
It helps check payment scenarios without affecting production data or money, while explaining each returned result.

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/straddleio/ai/sandbox-test
Clone the repo
git clone --depth 1 https://github.com/straddleio/ai
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,769 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 $0.00007 $0.01769
Opus 5 $0.00003 $0.00885
Sonnet 5 $0.00001 $0.00354
Haiku 4.5 $0.00001 $0.00177

Measured 2d ago against content hash 463f41603eb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sandbox-test 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.

providers/claude/plugin/commands/sandbox-test.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Straddle Sandbox Testing

If the user provided a scenario argument, jump directly to that scenario. Otherwise, present the list of available scenarios and ask which one to run.

General Rules

  • All testing happens in sandbox (https://sandbox.straddle.com). Never use production for testing.
  • Use the MCP straddle code tool for live execution against the sandbox API.
  • Explain each API response as it comes back. Do not silently move to the next step.
  • If a status is unexpected, use /explain-status to diagnose.
  • Generate unique external_id values for each test run to avoid idempotency collisions.
  • Always include Idempotency-Key headers on POST/PATCH requests.

Documentation Sources

Before walking through any scenario, search product docs for current sandbox simulation parameters:

Search product docs by POSTing to https://docs.straddle.com/mcp to find the current sandbox_outcomes parameter values and simulation mechanisms. Do not guess simulation parameters -- always verify against current documentation.

Available Scenarios

  1. payment-lifecycle -- Full charge from created through paid
  2. payout-flow -- Payout with funding timing explanation
  3. failures -- Simulated insufficient funds, closed account, risk review
  4. ach-returns -- Simulated ACH returns (R01, R02, R05, R07, R10, R29)
  5. funding -- Query funding events after settlement
  6. bridge -- Bridge token and paykey creation
  7. embed-onboarding -- Full Embed account onboarding flow
  8. webhooks -- Webhook testing with Svix

1. payment-lifecycle

Walk through the full charge lifecycle: customer creation through payment completion.

Steps:

  1. Create a customer with test identity data. Confirm status reaches verified.
  2. Connect a bank account via manual entry (routing: 110000000, account: 000123456789, type: checking). Extract the paykey.
  3. Create a charge for $100 (amount: 10000, currency: USD). Use consent_type: "internet" and today's date as payment_date.
  4. Check charge status. Walk through each transition: created -> scheduled -> pending -> paid.
  5. Explain what happened at each stage and what webhooks would fire.

Read the full file on GitHub · 167 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 · 167 lines · 7 tokens per session scan A 463f41603eb4

Subscribe to this mod's changes

sandbox-test is a command published in the GitHub repository straddleio/ai (5 stars, last pushed 3mo ago), licensed MIT. It adds 7 tokens to every session and 1,769 once invoked, about $0.0000 per session on Opus 5. 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.