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 johnqtcg/awesome-skills --skill e2e-testgit clone --depth 1 https://github.com/johnqtcg/awesome-skillsWrote 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/johnqtcg/awesome-skills/e2e-test)<a href="https://agentmods.dev/skills/johnqtcg/awesome-skills/e2e-test"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/e2e-test/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/johnqtcg/awesome-skills/e2e-test"><img src="https://agentmods.dev/badge/skills/johnqtcg/awesome-skills/e2e-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 4 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 | $0.00070 | $0.04668 |
| Opus 5 | $0.00035 | $0.02334 |
| Sonnet 5 | $0.00014 | $0.00934 |
| Haiku 4.5 | $0.00007 | $0.00467 |
Grade A, and why
e2e-test scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Read, Write, Grep, Glob, Bash(go test*), Bash(go vet*), Bash(npx playwright*), Bash(playwright*), Bash(npm run*), Bash(npm ci*), Bash(curl*), Bash(agent-browser*), Bash(bash scripts/*), Bash(python3 script How it starts
The opening of the file, as written. The whole thing — 471 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E test
Use this skill to create E2E coverage that is deterministic, evidence-backed, and maintainable in real repositories.
Quick Reference
| If you need to… | Go to |
|---|---|
| Design new E2E test coverage for a user journey | §Operating Model → new journey coverage + Load references/checklists.md |
| Write or update Playwright tests | §Runner Strategy + Load references/playwright-patterns.md |
| Use advanced Playwright (auth, fixtures, mocking, CI sharding) | Load references/playwright-deep-patterns.md |
| Triage a flaky or failing E2E test | §Operating Model → flaky triage + Load references/checklists.md |
| Use Agent Browser for exploration or repro | §Runner Strategy + Load references/agent-browser-workflows.md |
| Design CI gates for E2E suites | §Operating Model → CI gate design + Load references/environment-and-dependency-gates.md |
| Avoid common Playwright mistakes | Load references/anti-examples.md |
| Test content inside an iframe (payment, editor, OAuth) | Load references/playwright-deep-patterns.md §Iframes |
| Handle a Tauri or native-mobile app | §Version and Platform Gate → Platform Scope Boundary |
| Check generated spec code before reporting | Run python3 scripts/lint_e2e_spec.py <file.spec.ts> |
| See a fully worked E2E output example | Load references/golden-examples.md |
Do not use this skill for visual design review with no automated journey value, performance/load testing, or tests that would require guessed secrets, endpoints, or private accounts.
Load References Selectively
Load on demand, not up front. A typical Playwright coding task needs the two
every-task rows plus playwright-patterns.md — three files. Everything below that
is conditional; open it when the trigger in the first column actually applies.
| When | Load / run | Contents |
|---|---|---|
| Every task, before coverage or gate decisions | references/checklists.md |
5 checklists: pre-run readiness, journey coverage, flaky triage, quarantine, result reporting |
| Every task, before claiming runnable | references/environment-and-dependency-gates.md |
Readiness gates per context (local / preview / staging / CI), available vs declared vs missing, dependency matrix |
| Before gate decisions | bash scripts/discover_e2e_needs.sh |
Detects runner, Node, framework, existing tests, env-var states, CI platform. Report facts, not guesses |
| Writing Playwright code (JS only) | references/playwright-patterns.md |
Selector order (getByRole first), wait patterns, assertion contracts, config baseline, API-introduction + Node tables |
| Auth, fixtures, data isolation, mocking, iframes, sharding | references/playwright-deep-patterns.md |
The advanced layer — large; open the section you need |
| A mistake not among the seven below | references/anti-examples.md |
Extended catalog only, no overlap with §Anti-Examples here |
| Using Agent Browser | references/agent-browser-workflows.md |
Commands, exploration→code conversion, repro steps, handoff format |
| Shaping the final report | references/golden-examples.md |
Full output-contract examples (Playwright + Go). All figures in it are synthetic |
| Grading generated spec code | python3 scripts/lint_e2e_spec.py <file> |
Deterministic check of C1–C4 / S1 / S3 / S5 / H2 + W1. Evidence, not a verdict |
What ships with it
29 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.
- references/agent-browser-workflows.md 7.5 KB
- references/anti-examples.md 8.1 KB
- references/checklists.md 5.4 KB
- references/environment-and-dependency-gates.md 7.5 KB
- references/golden-examples.md 19 KB
- references/playwright-deep-patterns.md 32 KB
- references/playwright-patterns.md 12 KB
- scripts/discover_e2e_needs.sh 19 KB runs code
- scripts/lint_e2e_spec.py 29 KB runs code
- scripts/run_regression.sh 2.6 KB runs code
- scripts/tests/COVERAGE.md 17 KB
- scripts/tests/golden/001_new_login_journey.json 1.1 KB
- scripts/tests/golden/002_honest_scaffold_missing_account.json 1018 B
- scripts/tests/golden/003_flaky_triage_async_race.json 1.1 KB
- scripts/tests/golden/004_ci_gate_design.json 987 B
- scripts/tests/golden/005_agent_browser_exploration.json 1.2 KB
- scripts/tests/golden/006_no_base_url_stop.json 798 B
- scripts/tests/golden/007_serial_checkout_funnel.json 1.1 KB
- scripts/tests/golden/008_version_gate_old_playwright.json 827 B
- scripts/tests/golden/009_accessibility_audit.json 895 B
- scripts/tests/golden/010_visual_regression.json 786 B
- scripts/tests/golden/011_tauri_desktop.json 1.2 KB
- scripts/tests/golden/012_native_mobile_rejection.json 732 B
- scripts/tests/golden/013_multi_browser_matrix_ci.json 814 B
- scripts/tests/golden/014_iframe_embedded_content.json 954 B
- scripts/tests/test_discover_script.py 18 KB runs code
- scripts/tests/test_golden_scenarios.py 14 KB runs code
- scripts/tests/test_skill_contract.py 68 KB runs code
- scripts/verify_hook_semantics.sh 7.7 KB runs code
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 · 471 lines · 70 tokens per session scan A f0328535a645
e2e-test is a skill published in the GitHub repository johnqtcg/awesome-skills (30 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 4,668 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.
verification-engine
Use when verifying build/test/lint before commit, PR, or completion claims. Runs verification pipeline in fresh subagent context with auto-repair. Triggers on /handoff-verify, pre-commit check, build verification, test validation.
eval-harness
Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.
dependency-upgrade
Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.
webapp-testing
Write and run comprehensive web app tests — unit, integration, E2E with Playwright/Cypress, and visual regression.
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.