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 skills add hideokamoto/stripe-testing-mcp-tools --skill stripe-test-clock-constraintsgit clone --depth 1 https://github.com/hideokamoto/stripe-testing-mcp-toolsWrote 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/skills/hideokamoto/stripe-testing-mcp-tools/stripe-test-clock-constraints)<a href="https://agentmods.dev/skills/hideokamoto/stripe-testing-mcp-tools/stripe-test-clock-constraints"><img src="https://agentmods.dev/badge/skills/hideokamoto/stripe-testing-mcp-tools/stripe-test-clock-constraints/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/skills/hideokamoto/stripe-testing-mcp-tools/stripe-test-clock-constraints"><img src="https://agentmods.dev/badge/skills/hideokamoto/stripe-testing-mcp-tools/stripe-test-clock-constraints.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 | $0.00066 | $0.00684 |
| Opus 5 | $0.00033 | $0.00342 |
| Sonnet 5 | $0.00013 | $0.00137 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
stripe-test-clock-constraints 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 11d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stripe Test Clock Constraints
Quick reference for the rules and gotchas of Stripe test clocks as exposed by this MCP. Consult this before designing a time-simulation scenario.
Hard constraints
- Max 3 customers per clock.
create_stripe_test_customerswith atest_clockset rejectsnumber > 3. To exceed 3 customers in one scenario, use additional clocks. - Clock attachment is creation-time only. A customer can be linked to a
test clock only when it is created (
create_stripe_test_customerswithtest_clock). There is no way to attach or move an existing customer to a clock afterward, so create the clock first. - Advance is forward-only.
advance_stripe_test_clockcan only movefrozen_timeto a time after the current frozen time. You cannot rewind a clock; to test an earlier point, create a new clock. - Advance is asynchronous. After
advance_stripe_test_clock, the clock enters anadvancingstate and processes billing events in the background. The tool returns thestatusonce in its response, but this MCP server does not expose a tool to retrieve or re-poll the clock, so you cannot programmatically watch it reachready. If the response showsadvancing, wait a few seconds before follow-up operations, or have the user confirm the clock has settled in the Stripe Dashboard.
Time format
frozen_timeis a Unix timestamp in seconds (epoch seconds), not milliseconds and not an ISO string.- Convert carefully:
- Many languages give milliseconds (
Date.now()in JS) — divide by 1000 and floor. - From an ISO date: compute epoch seconds (for example, in shell
date -d '2024-02-01T00:00:00Z' +%s). - When reading a value back, multiply by 1000 to build a JS
Date.
- Many languages give milliseconds (
- A common bug is passing milliseconds, which lands the clock far in the future; double-check the magnitude (a 2024-2026 timestamp is ~1.7e9, a millisecond value is ~1.7e12).
Practical guidance
- Plan all the time points you need up front; since you cannot rewind, build a fresh clock per backward scenario.
- Keep the
test_clock_idreturned at creation; it is required for every advance. - To cross a billing boundary, advance to just past the subscription's
current_period_end. - For an end-to-end billing procedure, see
stripe-billing-cycle-test. - For setup/cleanup of the data around clocks, see
stripe-test-data-lifecycle.
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.
- 11d ago First seen · 56 lines · 66 tokens per session scan A cb8fd6c29f43
stripe-test-clock-constraints is a skill published in the GitHub repository hideokamoto/stripe-testing-mcp-tools (9 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 684 once invoked, about $0.0003 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.
Other skills, from other repositories
strategy-generate
Create, modify, and optimize quantitative trading strategies, then backtest and evaluate them.
health
Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application…
mt5-robot-tester
Select the best MetaTrader 5 trading robots (Expert Advisors) that have not been backtested yet, by running the MT5 Strategy Tester from the command line through a 3-round pipeline. Use when the user wants to batch-test MT5 bots/EAs, screen robots across all symbols, optimize EA parameters, or move candidate bots to…
prompt-proximity-architecture
Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…
walk-forward-validation
Walk-forward validation framework for trading strategies and ML models with time-series-aware splits, overfit detection, and regime-aware validation.
ln-41-test-strategy-planner
Plans a risk-based test portfolio and prioritized scenarios without editing tests. Not for test execution or implementation.