Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add alphabravo-oss/guild/plugin install e2eWrote 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/commands/alphabravo-oss/guild/write)<a href="https://agentmods.dev/commands/alphabravo-oss/guild/write"><img src="https://agentmods.dev/badge/commands/alphabravo-oss/guild/write/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/commands/alphabravo-oss/guild/write"><img src="https://agentmods.dev/badge/commands/alphabravo-oss/guild/write.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 | $0.00022 | $0.01072 |
| Opus 5.5 | $0.00009 | $0.00429 |
| Sonnet 5.5 | $0.00004 | $0.00214 |
| Haiku 4.5 | $0.00002 | $0.00107 |
Grade A, and why
write 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
4. Confirm their dev server is reachable at the baseURL in `playwright.config.ts`. Try `curl -sI $BASE_URL` (default `http://localhost:3000`). If unreachable, ask the user to start it. How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user wants you to write a Playwright E2E test for a specific user flow. Flow description is in $ARGUMENTS.
Preflight
- Confirm
playwright.config.tsexists in cwd. If not, tell them to run/e2e:initfirst and STOP. - Read
${CLAUDE_PLUGIN_ROOT}/skills/author/SKILL.md(or invoke the author skill) — it has the selector/wait/idempotency rules you must follow. - Confirm Playwright MCP tools are loaded (browser_navigate, browser_snapshot, etc.). If they aren't loaded, tell the user to restart Claude Code and STOP.
- Confirm their dev server is reachable at the baseURL in
playwright.config.ts. Trycurl -sI $BASE_URL(defaulthttp://localhost:3000). If unreachable, ask the user to start it.
For non-trivial flows: delegate to the spec-writer subagent
If the flow description is more than one screen of interaction (multi-step form, login + action, cross-page workflow), spawn the e2e:spec-writer agent. It runs in isolated context which keeps the MCP snapshot noise out of the main thread. Pass it the flow description, baseURL, and any constraints.
For simple single-action flows (one click, one assertion), do it inline — spawning an agent is overhead.
Procedure (inline path)
1. Slug the spec
Convert the flow description to a kebab-case slug. Example: "user logs in and sees dashboard" → login-shows-dashboard. Target path: tests/<slug>.spec.ts. If a file already exists at that path, append -2, -3, etc. — never silently overwrite.
2. Drive the browser
Use Playwright MCP:
browser_navigateto baseURL (and the starting route, if the flow names one).browser_snapshot— read the accessibility tree. Identify the elements you'll interact with by their roles and accessible names.- For each step in the user flow: pick the MCP tool that matches (
browser_click,browser_type,browser_select,browser_press_key, etc.) and execute. - After each step, take another
browser_snapshotto confirm the DOM changed as expected and to capture the post-state for assertions. - Note any console errors during the flow — they belong as assertions in the spec.
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 · 74 lines · 22 tokens per session scan A 696416f4cf8c
write is a command published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 11d ago), licensed MIT. It adds 22 tokens to every session and 1,072 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.
Other commands, from other repositories
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
amazing-e2e-check
Run explicitly requested E2E, browser, device, or installed-deployment scenarios in an independent verification workflow.
verify-pr
Verify a PR's frontend changes through browser automation.
auto-verify
A command for checking a website's front-end user experience with Playwright, a tool that automates web browsers.