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 tutur3u/platform --skill tuturuuu-e2e-auth-debugginggit clone --depth 1 https://github.com/tutur3u/platformWrote 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/tutur3u/platform/tuturuuu-e2e-auth-debugging)<a href="https://agentmods.dev/skills/tutur3u/platform/tuturuuu-e2e-auth-debugging"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-e2e-auth-debugging/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/tutur3u/platform/tuturuuu-e2e-auth-debugging"><img src="https://agentmods.dev/badge/skills/tutur3u/platform/tuturuuu-e2e-auth-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.01023 |
| Opus 5.5 | $0.00011 | $0.00409 |
| Sonnet 5.5 | $0.00006 | $0.00205 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
tuturuuu-e2e-auth-debugging 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 6d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tuturuuu E2E Auth Debugging
Core Workflow
Use this skill when an E2E or integration test fails around login, local
dev-session, onboarding redirects, guest access, app-session verification, or
rate-limit auth state.
Start by reading AGENTS.md, checking git status --short, and identifying
whether another coordination note owns the same E2E or auth files.
Safety First
- Keep E2E helpers local-only. Do not relax production auth, onboarding, workspace, or rate-limit guards to make a test pass.
- Use
apps/web/e2e/helpers/environment.tsandassertSafeE2EEnvironment()for tests that touch local Supabase or app coordination secrets. - Use unique test emails and clean/reset only test-owned local state.
- Finite builds may validate authorized changes; start long-lived servers only for requested runtime verification.
Native E2E First
For local E2E debugging and patch iteration, run the web app and Playwright on
the native machine. Do not use bun test:e2e, bun --cwd apps/web test:e2e,
or bun test:e2e:web:docker as the first debugging path; those commands build
and run the production-style Docker web stack and are slower to patch.
Use Docker-backed web E2E only when the user explicitly asks for Docker or CI parity, or when the suspected bug is specific to the production Docker runtime. If your own Docker web E2E run is already in progress and native debugging is more appropriate, stop your run before switching. Leave other sessions' runs alone and wait for resource admission.
The native workflow still uses local Supabase. Keep all E2E origins local and do not point browser tests at a cloud Supabase project.
Native Run Shape
- Start or reset the local Supabase stack with the database package scripts.
- Start
apps/webnatively with the local E2E environment. For a native server, server-side Supabase URLs should resolve tohttp://127.0.0.1:8001, not Docker-onlyhost.docker.internal. - Run the focused Playwright spec directly from
apps/webagainst the native server:
What ships with it
1 file 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.
- 6d ago Changed · +8 lines 0771cd04dfd8
- 1mo ago Changed · +1 lines 19f656c55416
- 1mo ago Changed · -31 tokens per session 08a30edb439b
- 1mo ago First seen · 92 lines · 59 tokens per session scan A 6b4e0c1db144
tuturuuu-e2e-auth-debugging is a skill published in the GitHub repository tutur3u/platform (55 stars, last pushed today), licensed Apache-2.0. It adds 28 tokens to every session and 1,023 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
quality-engineering-test-healing
Failure taxonomy and allowed/forbidden repairs for a failing E2E test. Use when a Playwright/Maestro/Detox/XCUITest/Espresso/Appium test fails and you must decide whether to repair the test or route to a real bug.
handle-regression
Protocol for detecting, isolating, and fixing regressions in test262 pass count. Use when a test run shows fewer passes than expected.
systematic-debugging
4-phase systematic debugging methodology with root cause analysis and evidence-based verification. Use when debugging complex issues.
playwright-e2e-testing
Production-grade Playwright end-to-end testing skill for AI coding agents. Provides specialized guidance for writing, debugging, and maintaining Playwright tests in TypeScript, JavaScript, and Python. Covers the full testing lifecycle: test structure and architecture (Page Object Model, fixtures, custom matchers)…