Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add PaymobAccept/Paymob-AI-Integration-Skill/plugin install paymob-integrationWrote 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/paymobaccept/paymob-ai-integration-skill/paymob-test-cards)<a href="https://agentmods.dev/commands/paymobaccept/paymob-ai-integration-skill/paymob-test-cards"><img src="https://agentmods.dev/badge/commands/paymobaccept/paymob-ai-integration-skill/paymob-test-cards/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/paymobaccept/paymob-ai-integration-skill/paymob-test-cards"><img src="https://agentmods.dev/badge/commands/paymobaccept/paymob-ai-integration-skill/paymob-test-cards.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00016 | $0.00680 |
| Opus 5 | $0.00008 | $0.00340 |
| Sonnet 5 | $0.00003 | $0.00136 |
| Haiku 4.5 | $0.00002 | $0.00068 |
Grade A, and why
paymob-test-cards 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 10d 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.
What it actually says
Read references/test-credentials.md in full and present the sandbox test credentials it contains to the user. Do not use any test numbers from memory — this file is the only source.
Locating the reference file. Use the first of these that exists:
${CLAUDE_PLUGIN_ROOT}/skills/paymob-integration/references/— plugin install~/.claude/skills/paymob-integration/references/— personal skill install.~is the user's home directory; on Windows expand it yourself (%USERPROFILE%\.claude\skills\…), since a literal~will not resolve there.skills/paymob-integration/references/— repository checkout, relative to the working directory
${CLAUDE_PLUGIN_ROOT} is substituted only for plugin installs. If you see it unexpanded, you are not in one — use path 2 or 3. If none resolve, search for test-credentials.md under any paymob-integration directory.
If you cannot read the file, say so and stop. Do not list card numbers from memory — stale or invented test credentials waste a merchant's debugging time on a payment that was never going to succeed.
Argument handling for $ARGUMENTS:
card→ show only the Mastercard and Visa test card sections.wallet→ show only the test mobile wallet section.kiosk,bnpl, or a named BNPL provider (Valu, Souhoola, Tabby, Tamara, Sympl, …) → report what the file's Methods with no sandbox test path section says. Do not offer a workaround that section doesn't list, and do not substitute a test card so the method looks covered.- Any other method the file has no section for (Apple/Google Pay, bank installments) → say plainly that the file has no entry for it, then point the user to
references/live-resources.md(thellms.txtdoc index and developer docs) or[email protected]. Do not invent numbers, and do not substitute a card number as a stand-in. Do not assert how that method's sandbox flow works either — if it isn't in the reference file, it isn't established here. - No argument → show all sections the file contains (cards and wallet).
Always carry over, verbatim in meaning, these two caveats from the source file regardless of which filter was used:
- Sandbox test transactions/intentions expire after 30 days — a full test flow must be completed within that window.
- Paymob does not officially document separate decline/error-simulation test numbers. If the user needs to test a decline or failure path, tell them to confirm with their Paymob account manager or
[email protected]rather than guessing, since reusing a success-only test card with wrong details may just retry instead of declining.
Remind the user these are Test-mode only — never valid against Live keys or Live Integration IDs, and never real card data.
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.
- 10d ago First seen · 31 lines · 16 tokens per session scan A 7598e70142ef
paymob-test-cards is a command published in the GitHub repository PaymobAccept/Paymob-AI-Integration-Skill (30 stars, last pushed 25d ago), licensed MIT. It adds 16 tokens to every session and 680 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
burn-rate
Compute the recent 7-day spend trend (burn rate) from daily sessions and per-session cost.
secular-trends
Secular technology trends analysis — technology adoption cycles, disruption risk, strategic positioning.
earnings
Post-earnings analysis for a stock — fast in-chat summary card by default, full Markdown research report on request.
monitor
AML transaction monitoring and suspicious activity reporting.
signed-policy-agentic-commerce
Run an agentic commerce chain under a signed Work Mandate, trip the escalation gate on purpose, and replay the gates on the ledger.
budget
Marks the cheapest Claude model and effort that still clears this task with high confidence. Still shows the full Budget, Optimal, and Splurge spread.