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/paypal/ai-toolkit/test-accountsgit clone --depth 1 https://github.com/paypal/AI-ToolkitWrote 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/paypal/ai-toolkit/test-accounts)<a href="https://agentmods.dev/commands/paypal/ai-toolkit/test-accounts"><img src="https://agentmods.dev/badge/commands/paypal/ai-toolkit/test-accounts.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 | $0.00011 | $0.00990 |
| Opus 5 | $0.00005 | $0.00495 |
| Sonnet 5 | $0.00002 | $0.00198 |
| Haiku 4.5 | $0.00001 | $0.00099 |
Grade A, and why
test-accounts scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X POST https://api-m.sandbox.paypal.com/v1/oauth2/token \ How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
If "$ARGUMENTS" is set, show only the section(s) relevant to that scenario plus the Key Gotchas. If empty, show all sections.
Sandbox Buyer & Seller Accounts
Create test accounts at https://developer.paypal.com/dashboard/accounts. Two types:
| Type | Purpose |
|---|---|
| Personal (Buyer) | Approves payments, Venmo, Pay Later, opens disputes |
| Business (Seller/Merchant) | Receives payments, creates orders, invoices, subscriptions |
Sandbox base URL: https://api-m.sandbox.paypal.com
Quick Access Token (Sandbox)
curl -X POST https://api-m.sandbox.paypal.com/v1/oauth2/token \
-u "$PAYPAL_CLIENT_ID:$PAYPAL_CLIENT_SECRET" \
-d "grant_type=client_credentials"
Test Scenarios
Successful Payment
Use any sandbox buyer account with sufficient balance. Amount: any normal value.
Declined Payment
To simulate declines, use sandbox buyer accounts with specific wallet configurations or use these trigger amounts (USD):
| Trigger | How to simulate |
|---|---|
| Instrument declined | Use a sandbox buyer card set to "Declined" in the sandbox account wallet |
| Insufficient funds | Set the sandbox buyer balance below the order amount |
| Risk decline | Use amounts configured in your sandbox to trigger TRANSACTION_REFUSED |
BNPL / Pay Later
- Use order amounts between $30–$1,500 (Pay in 4) or $199–$10,000 (Pay Monthly)
- The Pay Later option appears in the sandbox buyer approval window
- Sandbox does not simulate installment billing — only the initial capture is tested
Pay with Venmo
- Venmo sandbox does not invoke the real Venmo app
- During sandbox approval, select "Venmo" in the funding source picker
- Confirm
payment_source.venmoin the capture response
Subscriptions
- Create product → create plan (must be
ACTIVE) → create subscription - Approve using a sandbox buyer account
- Sandbox auto-processes renewal cycles — accelerate via the Developer Dashboard
- Use the Webhooks Simulator to test
BILLING.SUBSCRIPTION.PAYMENT.FAILEDand other lifecycle events
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 · 104 lines · 11 tokens per session scan A c42357e56281
test-accounts is a command published in the GitHub repository paypal/AI-Toolkit (12 stars, last pushed 16d ago), licensed Apache-2.0. It adds 11 tokens to every session and 990 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
cli-tools-over-mcp-for-tokens
Prefer giving agents small CLI tools over MCPs: a CLI is read once then driven by command, is deterministic, self-documents via --help, and costs far less context than an MCP's loaded tool schemas.
custom-clarifying-questions-slash-command
Package the "ask before you build" habit into a reusable custom slash command: it captures the task, asks 5 clarifying questions, drafts a plan, and waits for approval before executing.
effort-control-for-token-intensive-work
/effort sets how deeply the model reasons: low is fast and shallow, the default is high, and extra-high/max are slower but markedly more careful, switch up for risky or complex changes, back down for routine ones, and check the cost with /usage afterwards.
environment-switching-local-cloud-ssh
The environment selector at the bottom of Claude Code switches where work executes: local for fast interactive iteration, cloud (Anthropic servers) for routines that must run with your machine off, SSH for driving a remote box like a VPS.
inline-bash-in-slash-commands
TL;DR: Embed bash in a slash command to pre-compute state (e.g. git status) so the model gets the context for free instead of round-tripping for it.
learn
Force claude-smart to extract learnings from this session now.