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 JeonJe/claude-plugins --skill e2e-checklistgit clone --depth 1 https://github.com/JeonJe/claude-pluginsWrote 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/jeonje/claude-plugins/e2e-checklist)<a href="https://agentmods.dev/skills/jeonje/claude-plugins/e2e-checklist"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/e2e-checklist.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 5.1 | $0.00094 | $0.01449 |
| Opus 5 | $0.00047 | $0.00724 |
| Sonnet 5 | $0.00019 | $0.00290 |
| Haiku 4.5 | $0.00009 | $0.00145 |
Grade A, and why
e2e-checklist 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 7d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E checklist execution
Execute an already planned user flow against the real runtime, capture evidence, and produce a runtime-verification artifact. This skill does not own environment implementation or product/test code changes — it runs and records. For open-ended scenario discovery, use qa-scenarios instead of silently expanding the checklist.
References index
| File | When to read |
|---|---|
| references/playwright-regression-gate.md | The plan requires a deterministic browser regression guard; Gate A/B execution |
| references/gate-b-checklist.md | Human-judgment dump for Gate B |
| references/gate-interview.md | Mandatory human interview before passing a gate |
Core discipline
Screenshot-after-action (enforced)
Immediately after every meaningful action (click, submit, navigation, modal trigger), verify state with one of: a screenshot, a deterministic DOM eval, or an accessibility snapshot. Never assume an action succeeded — confirm the screen changed with evidence before the next step. Exceptions: intermediate typing (verify once after the last character), hover/focus (verified by the subsequent click's result).
Evidence rigor ladder
For the same claim, attempt the strongest evidence first (priority, not a ban on weaker tiers):
⓪ direct read of persisted state (DB/log store — strongest for state claims) > ① deterministic eval returning structured data (strongest for UI claims) > ② accessibility-snapshot element match > ③ before/after comparison > ④ screenshot + visual judgment — visual-only properties, always naming what is evaluated
A value claim like "the badge count is 3" is verified by DOM eval (①), not screenshot reading (④). A report whose PASSes are mostly ④ is itself a risk signal.
Auth wall stop (enforced)
On redirect to a login page or an auth modal: stop immediately; never auto-type credentials. Report to the user and delegate (manual login, then continue). Pre-agreed automated paths (test account on a dev environment) are the only exception.
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.
- 7d ago First seen · 109 lines · 94 tokens per session scan A 8e0683dcc424
e2e-checklist is a skill published in the GitHub repository JeonJe/claude-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,449 once invoked, about $0.0005 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
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
testing
Testing patterns with Vitest and Playwright for NestJS backend services. Use when writing unit tests, integration tests, or E2E tests for controllers, services, guards, and pipes.
api-tester
A tool for creating and checking API tests from the real API contract and implementation. An API is the agreed way that software sends requests and receives responses.
memstack-development-webapp-testing
Use when the user says 'write browser tests', 'test this page', 'playwright test', 'e2e test', 'end to end test', 'browser test', 'test the UI', or needs Playwright-based browser testing for a web application. Do NOT use for unit tests, API tests, or non-browser testing.
playwright-testing
E2E testing with Playwright - Page Objects, cross-browser, CI/CD.
visual-validation
Every UI change should be visually verified before it ships. Peekaboo captures pixel-accurate screenshots. The system compares before/after and flags visual regressions. No manual "looks good to me" — the machine verifies what the machine built.