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 JotJunior/cstk --skill e2e-integration-flowgit clone --depth 1 https://github.com/JotJunior/cstkWrote 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/jotjunior/cstk/e2e-integration-flow)<a href="https://agentmods.dev/skills/jotjunior/cstk/e2e-integration-flow"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/e2e-integration-flow/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/jotjunior/cstk/e2e-integration-flow"><img src="https://agentmods.dev/badge/skills/jotjunior/cstk/e2e-integration-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 86 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 246 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 247 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 248 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 249 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00113 | $0.03851 |
| Opus 5.5 | $0.00045 | $0.01540 |
| Sonnet 5.5 | $0.00023 | $0.00770 |
| Haiku 4.5 | $0.00011 | $0.00385 |
Grade A, and why
e2e-integration-flow 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 1mo 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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Integration Flow Skill
Author and run end-to-end integration tests that prove a feature actually works across the whole stack — not just that a button is clickable, but that every meaningful action produces the right effect at every layer it touches: UI → network/API → database → message queue → downstream side effects.
The driver is Playwright (browser automation for the frontend). The
differentiator is that Playwright is only the entry point: each UI step is
paired with assertions in the layers behind it. A test that fills a form and
sees a toast is a UI test. A test that fills a form, sees the toast, confirms
the row landed in the database with the right fields, and confirms the
user.created event reached the queue — that is an integration flow test.
Scope & limits. This skill builds and runs automated functional integration tests. It is not a load/performance test, not a security pentest (use
owasp-security), and not a substitute for unit tests. It assumes you can reach a running stack (frontend + backend + datastores) in a test/staging environment. Stack-agnostic core with concrete defaults — adapt commands and selectors to the project you are in.
Arguments
$ARGUMENTS is the feature/flow to test (e.g. "cadastro de cliente", "checkout
com cupom") or a path to its spec/UC (e.g. docs/specs/cadastro/spec.md,
docs/02-requisitos-casos-uso/UC-CAD-001.md). If empty, ask what flow to cover
and whether a spec/UC exists.
The mental model: a flow is a chain of contracts
Most flaky, low-value e2e suites fail because they treat the UI as the whole system. The fix is to think of the feature as an ordered flow contract:
For each user action, there is an observable consequence in one or more layers. The test asserts that consequence — at the deepest layer that is practical — before moving to the next action.
A registration flow is not "click, type, click". It is:
| # | User action | UI effect | Network | Database | Queue / async | Downstream |
|---|---|---|---|---|---|---|
| 1 | Log in | redirect to dashboard | POST /auth 200 + cookie |
session row (opt) | — | — |
| 2 | Open "New customer" | form renders | GET /form-meta 200 |
— | — | — |
| 3 | Submit invalid email | inline error, no submit | no POST fired |
no new row | — | — |
| 4 | Submit valid form | success toast, redirect | POST /customers 201 |
customers row w/ fields |
customer.created on exchange |
welcome email enqueued |
| 5 | (async) | list shows new customer | GET /customers includes it |
— | consumer ACKed | email sent |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +4 tokens per session 6e9bfe350430
- 2mo ago First seen · 316 lines · 109 tokens per session scan A 07f15b48de8b
e2e-integration-flow is a skill published in the GitHub repository JotJunior/cstk (24 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 3,851 once invoked, about $0.0005 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 2026-08-30.
e2e-integration-flow compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| e2e-integration-flowJotJunior/cstk | Skill | 24 | yesterday | MIT | A | 113 | Claude Code |
| agent-production-validatorruvnet/ruflo | Skill | 81k | yesterday | MIT | A | 16 | Claude Code |
| qa-acceptancepaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 38 | Claude Code, Codex |
| agent-testerruvnet/ruflo | Skill | 81k | yesterday | MIT | A | 15 | Claude Code |
| test-reportingaden-hive/hive | Skill | 11k | 4d ago | Apache-2.0 | A | 0 | Claude Code |
| verifyHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 25 | Claude Code, Codex |
| webapp-testingHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 32 | Claude Code, Codex |