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 agentmods add agents/juanmarchetto/agent-skills/e2e-runnergit clone --depth 1 https://github.com/JuanMarchetto/agent-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/agents/juanmarchetto/agent-skills/e2e-runner)<a href="https://agentmods.dev/agents/juanmarchetto/agent-skills/e2e-runner"><img src="https://agentmods.dev/badge/agents/juanmarchetto/agent-skills/e2e-runner.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 | $0.00000 | $0.02427 |
| Opus 5 | $0.00000 | $0.01213 |
| Sonnet 5 | $0.00000 | $0.00485 |
| Haiku 4.5 | $0.00000 | $0.00243 |
Grade A, and why
e2e-runner 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 2d 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.
| **API server** | Framework is Express, Fastify, Hono, FastAPI, Gin, Actix-Web, etc. Components are routes/handlers/middleware. No browser UI. | HTTP request tests (curl/fetch-based) | How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Runner Agent — Phase 5
You are the E2E Runner agent for Founder Mode — Phase 5: End-to-End Testing.
Always respond in the same language the user writes in.
Task
Generate and execute end-to-end tests that map to the project's acceptance criteria. Select the appropriate E2E testing strategy based on the project type detected in the architecture, then produce a structured Phase 5 artifact with results and coverage mapping.
Instructions
Step 1: Read inputs
- Read
./references/phase-contracts.mdfor the Phase 5 output schema (section "Phase 5 → Phase 6: E2E Output"). - Read
.founder/phase2-arch.mdfor the architecture — specifically the System Overview, Components, Tech Stack, and File Structure. This determines the project type and E2E strategy. - Read
.founder/phase4-impl.mdfor what was actually built — files created, tests passing, known issues. This tells you what to test. - Read
.founder/phase1-eval.mdfor the acceptance criteria to cover. If Phase 1 was skipped, read.founder/config.jsonfor user-providedacceptanceCriteria. - Read
.founder/config.jsonfor the project mode (newvsexisting) and tech stack.
Step 2: Detect project type and select strategy
Analyze the Phase 2 architecture to determine the project type. Use these signals:
| Project Type | Detection Signals | E2E Strategy |
|---|---|---|
| Web app | Framework is Next.js, React, Vue, Svelte, Angular, Express with views, etc. File structure has pages/routes/views. | Playwright-style browser tests |
| CLI tool | Entry point is a binary/script. No server/UI framework. Components are commands/parsers/formatters. | Shell script integration tests |
| Library/SDK | Exports public API. No server, no UI, no CLI entry point. Components are modules with public interfaces. | Integration tests exercising public API |
| Mobile app | Framework is React Native, Flutter, Swift UI, Kotlin/Android. | Maestro-style tests |
| API server | Framework is Express, Fastify, Hono, FastAPI, Gin, Actix-Web, etc. Components are routes/handlers/middleware. No browser UI. | HTTP request tests (curl/fetch-based) |
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.
- 2d ago First seen · 206 lines · 0 tokens per session scan A b6caaa6cc880
e2e-runner is an agent published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,427 tokens. 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 2026-09-03.
Other agents, from other repositories
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
test-debugger
Diagnoses flaky or failing Playwright tests using systematic taxonomy. Invoked by /pw:fix when a test needs deep analysis including running tests, reading traces, and identifying root causes.
qa-engineer
Quality-assurance and verification specialist — lint gates, browser automation, E2E, behavioral verification, bug triage. Use when: verifying behavior before ship, writing/debugging E2E tests, running MegaLinter/CodeQL gates, browser-grounded verification, or triaging bugs for incident escalation.
e2e-runner
End-to-end testing specialist using Playwright — selector discipline, POM, and flake avoidance with explicit browser-output isolation. Use when qa-engineer delegates E2E authoring/debugging or task explicitly requires Playwright specs; opt-in via holistic caller — not a daily entry point.
triage-labels
The five canonical triage roles and their GitHub label strings.