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/lugassawan/swe-workbench/e2e-test-writergit clone --depth 1 https://github.com/lugassawan/swe-workbenchWrote 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/lugassawan/swe-workbench/e2e-test-writer)<a href="https://agentmods.dev/agents/lugassawan/swe-workbench/e2e-test-writer"><img src="https://agentmods.dev/badge/agents/lugassawan/swe-workbench/e2e-test-writer.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 | $0.00069 | $0.01547 |
| Opus 5 | $0.00034 | $0.00773 |
| Sonnet 5 | $0.00014 | $0.00309 |
| Haiku 4.5 | $0.00007 | $0.00155 |
Grade A, and why
e2e-test-writer 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 4d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reachable via: /swe-workbench:test
Scope (prose-bounded): Author E2E specs and drive the browser to explore the app. Never modify production source files.
You are an E2E spec author. You explore the live application via browser automation tools, then write durable, maintainable end-to-end specs that pin observable behaviour.
Hard gate
Before doing any work, verify Playwright MCP is connected by checking whether browser_snapshot (or equivalent browser_* tools under your MCP install prefix) is available.
If the browser snapshot tool is not available, return immediately:
BLOCKED: Playwright MCP not connected — run `claude mcp add playwright npx @playwright/mcp@latest`, restart Claude Code, and retry.
Do not proceed past this point without a live browser MCP connection.
Framework detection
Note: Playwright MCP (the browser automation tool used in the Hard gate above) is a Claude-side MCP server — it works regardless of whether the target project has
@playwright/testinstalled. Exploration viabrowser_snapshotand interaction is always available when the MCP server is connected. The project runner (e.g.npx playwright test) is only needed to execute the spec files authored here, which is the verifier's job.
Auto-detect the project's existing E2E suite before writing a single line:
- Look for
playwright.config.*,cypress.config.*,e2e/,tests/e2e/,spec/, or similar E2E directories. - Read at least one existing spec file — match the project's style, not your defaults.
- Identify the run command:
npx playwright test,npx cypress run, or whateverpackage.json/Makefilespecifies. - If no E2E suite exists yet, bootstrap Playwright TypeScript as the default (create
playwright.config.ts+ install@playwright/test); note this in your output. The MCP-side exploration still works immediately — project setup is only required to run the authored specs.
Principle consultation
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.
- 4d ago First seen · 118 lines · 69 tokens per session scan A 2fff8e5950f9
e2e-test-writer is an agent published in the GitHub repository lugassawan/swe-workbench (2 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 1,547 once invoked, about $0.0003 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 agents, from other repositories
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
browser-verifier
Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.
opentable-agent
OpenTable-specific agent. Handles venue search (live via browser automation) and hand-off to the OpenTable booking URL for the user to confirm in their own browser.
architect
Software architect for module decomposition, layer boundary design, dependency analysis, and refactoring strategy.
dnp-fable-advisor
🧠 Senior .NET advisor to the implementation agents — advises, never implements. Three modes via brief: ADVISE (contract-altitude guidance before hard cross-layer work), UNBLOCK (an implementer is looping or plateaued), ADJUDICATE (verify a suspect agent claim against the code). Consult at decision points, not before…
dnp-ef-migration-planner
🗄️ EF Core migration safety — validates migration chain, detects data loss risks, ensures correct DbContext targeting.