LangWatch is a platform for testing, evaluating, and monitoring LLM-powered agents before release and in production. Teams use it to run agent simulations, trace and evaluate behavior, improve prompts and models, review failures, and manage provider costs and governance.
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 langwatch/langwatch --skill paymentsimgit clone --depth 1 https://github.com/langwatch/langwatchWrote 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/langwatch/langwatch/paymentsim)<a href="https://agentmods.dev/skills/langwatch/langwatch/paymentsim"><img src="https://agentmods.dev/badge/skills/langwatch/langwatch/paymentsim/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/langwatch/langwatch/paymentsim"><img src="https://agentmods.dev/badge/skills/langwatch/langwatch/paymentsim.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 | $0.00110 | $0.01255 |
| Opus 5.5 | $0.00044 | $0.00502 |
| Sonnet 5.5 | $0.00022 | $0.00251 |
| Haiku 4.5 | $0.00011 | $0.00126 |
Grade A, and why
paymentsim 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
paymentsim
Fakes exactly the Stripe surface enterprise/modules/billing calls, in Stripe's wire shapes
(form bodies, list/search/error envelopes, Idempotency-Key replay), and signs webhooks with
Stripe-Signature: t=<unix>,v1=<hmac> so billing's real constructEvent verifies them. Ids
are counters (cus_sim000001); catalog prices keep their real ids. Code: services/sims/paymentsim;
spec: specs/setup/payment-simulator.feature. State is in memory: a restart forgets it.
Run it
- Every
haven upruns it; local and CI stacks need no Stripe account. When.envand the shell name none ofSTRIPE_SECRET_KEY,STRIPE_WEBHOOK_SECRET,STRIPE_API_BASE, the app getsSTRIPE_API_BASE=https://payment.<slug>.langwatch.localhost,STRIPE_SECRET_KEY=sk_test_paymentsim,STRIPE_WEBHOOK_SECRET=whsec_paymentsim. Set your own Stripe test keys in.envand those are used as they are.haven upprints which:Stripe: paymentsimorStripe: your key from .env. - A key kept only in 1Password loses: haven sees no key, injects paymentsim's, and env answers first.
haven up -paymentdrops the lane (sticky). Restart the API (haven down+up) after toggling.- Without haven:
make service svc=paymentsimwithPAYMENTSIM_ADDR(default:5599),PAYMENTSIM_WEBHOOK_URL,PAYMENTSIM_WEBHOOK_SECRET,PAYMENTSIM_CATALOG,PAYMENTSIM_PUBLIC_URL.
Stripe surface
customers create/retrieve/del · prices list (expand[]=data.product) · subscriptions
create/retrieve/update/cancel · checkout sessions create + line_items · billing portal
sessions · invoices create/list/search/retrieve/finalize/pay/create_preview · invoiceitems
create · billing meter_events create, meters list, event_summaries (minute-aligned) ·
billing credit_grants create. Anything else answers Stripe's 404 "Unrecognized request URL".
Events fired: checkout.session.completed, customer.subscription.created|updated|deleted,
invoice.finalized|paid|payment_succeeded|payment_failed.
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.
- 3d ago First seen · 72 lines · 110 tokens per session scan A 23a745929848
paymentsim is a skill published in the GitHub repository langwatch/langwatch (4,958 stars, last pushed today), licensed Apache-2.0. It adds 110 tokens to every session and 1,255 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-13.
Other skills, from other repositories
ai-prompt-regression-testing
Use when comparing prompt changes against a fixed evaluation set: record actual model settings, required checks, missing results, judge limitations and case-level regression evidence.
trulens-evaluation-workflow
Systematically evaluate your LLM application with TruLens.
trulens-running-evaluations
Execute TruLens evaluations and view results.
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.
testing
Verify a Skyvern deployment is working correctly by smoke-testing the backend API, frontend rendering, browser session provisioning, and workflow execution. Use when the user says 'is Skyvern working', 'test my deployment', 'verify the installation', 'smoke test', or needs to check that a self-hosted or local Skyvern…