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 ryan-haver/fusebase-mcp --skill app-e2e-testsgit clone --depth 1 https://github.com/ryan-haver/fusebase-mcpWrote 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/ryan-haver/fusebase-mcp/app-e2e-tests)<a href="https://agentmods.dev/skills/ryan-haver/fusebase-mcp/app-e2e-tests"><img src="https://agentmods.dev/badge/skills/ryan-haver/fusebase-mcp/app-e2e-tests/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/ryan-haver/fusebase-mcp/app-e2e-tests"><img src="https://agentmods.dev/badge/skills/ryan-haver/fusebase-mcp/app-e2e-tests.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 | $0.00088 | $0.01503 |
| Opus 5.5 | $0.00035 | $0.00601 |
| Sonnet 5.5 | $0.00018 | $0.00301 |
| Haiku 4.5 | $0.00009 | $0.00150 |
Grade A, and why
app-e2e-tests 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.
This is a copy
100% identical to app-e2e-tests — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App E2E tests (environment-aware)
One suite in tests/e2e/, same specs against every environment of the
project. Environments (fusebase env) supply everything varying between
stages: base URLs, org/app ids, test users.
When e2e is being added as part of an environment migration, first follow the local guide App Environment Migration Guide, then use this skill for the Playwright harness and CI details.
When adding e2e to an existing project, first follow the local guide E2E Playwright Setup Guide: audit environments, prefer non-prod targets, warn before any prod run, scaffold from the CLI template, and wire GitLab CI.
Scaffold
fusebase scaffold --template e2e --dir tests/e2e
cd tests/e2e && npx playwright install chromium
FUSEBASE_ENV=<env> npm test
Layout — one project per app
playwright.config.ts generates one Playwright project per app in
fusebase.json (name = the app's key, falling back to subdomain), each
pinned to that app's env-effective URL. Specs live in:
specs/common/**— universal specs, run for EVERY app, app-aware viatest.info().project.name.specs/<appKey>/**— that app's own specs.
Adding an app: give it a short key in fusebase.json (e.g. probe),
mkdir specs/<key>, add specs, add the key to the CI matrix APP list. Run a
single app with --project=<appKey>.
Cross-app / portal flows (registration → access propagation across apps +
portal) span more than one app and have NO single baseURL — they do not
belong to any app's project. Put them in specs/integration/; the config
adds an integration project whose specs build each app's URL via
appBaseUrl(env, key). Add integration to the CI matrix APP list.
Recipes: examples/cross-app-access.spec.ts, examples/portal-access.spec.ts.
(Product-scoped magic links + one org = shared session across app subdomains,
which is exactly what these flows assert.)
Non-negotiables
- Stage guard stays.
specs/common/stage.spec.tsasserts each app's deployedfusebase-env.jsonmatches the target env AND app. Never delete it — a run against the wrong stage/app is worse than no run. - No hardcoded env data. Hosts, org/app ids, credentials come only from
helpers/env.ts(environments/<name>.json+.env.<name>) and the project'sbaseURL. A spec that embeds a URL or id silently breaks on another environment or app. - Fixtures self-skip. Use the
fixtureUser(env, key)+test.skippattern (seeexamples/role-matrix.spec.ts) so specs stay runnable while fixtures roll out per env. - Cleanup. Tests that create data must delete it — prod-test environments are real orgs.
- No secrets in git. Passwords via
PW_USER_<KEY>_PASSWORDin.env.<name>locally / CI variables in pipelines. Reports and traces are gitignored.
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 First seen · 121 lines · 88 tokens per session scan A 01255cc713d7
app-e2e-tests is a skill published in the GitHub repository ryan-haver/fusebase-mcp (8 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 1,503 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to app-e2e-tests, differing in 0 lines, and is treated as a copy.
app-e2e-tests compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| app-e2e-testsryan-haver/fusebase-mcp | Skill | 8 | 3d ago | MIT | A | 88 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 68 | Claude Code, Codex |
| create-verification-skillget-bb/bb | Skill | 5.1k | today | MIT | A | 57 | Claude Code, Codex |
| webapp-testinganthropics/skills | Skill | 189k | yesterday | none | A | 35 | Claude Code |
| browser-qahashgraph-online/awesome-codex-plugins | Skill | 1.5k | today | Apache-2.0 | A | 58 | Claude Code, Codex |
| test-electron-appPostHog/posthog-foss | Skill | 728 | today | MIT | A | 112 | Claude Code |
| smoke-testSkyvern-AI/skyvern | Skill | 23k | today | AGPL-3.0 | A | 50 | Claude Code, Codex |