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 commands/alphabravo-oss/guild/recordgit clone --depth 1 https://github.com/alphabravo-oss/guildWhat 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 | $0.00018 | $0.00735 |
| Opus 5 | $0.00009 | $0.00367 |
| Sonnet 5 | $0.00004 | $0.00147 |
| Haiku 4.5 | $0.00002 | $0.00073 |
Grade A, and why
record 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 yesterday.
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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The user wants to record a flow manually with Playwright's recorder. Slug is in $ARGUMENTS.
When to use this vs /e2e:write:
/e2e:write— Claude drives the browser via MCP. Good for flows Claude can perform autonomously (clear instructions, deterministic)./e2e:record— Human drives. Good for flows that are hard to describe in words (drag gestures, file uploads, anything with sensitive credentials Claude shouldn't see).
Preflight
playwright.config.tsexists.- Dev server is reachable at baseURL.
- The cwd has access to a display —
playwright codegenopens a real browser window. If on a headless server, this command does not apply; tell the user and exit.
Procedure
1. Slug + path
Convert $ARGUMENTS to kebab-case. Target: tests/<slug>.spec.ts. Refuse to overwrite an existing file — bump to <slug>-2.spec.ts.
2. Launch codegen
npx playwright codegen --output tests/<slug>.spec.ts $BASE_URL
Where $BASE_URL comes from playwright.config.ts (read it, don't hardcode). The recorder opens a browser window AND an inspector — the user clicks around, the inspector writes code in real time.
Tell the user:
- "A browser window has opened. Perform the flow you want to capture."
- "Close the browser window when done. Codegen will save the spec automatically."
3. Wait for codegen to exit
This is a foreground command — it blocks until the user closes the recorded browser. Don't run it in the background; you need the exit signal.
4. Post-process
When codegen exits, read the generated file. It will be functional but rough — codegen produces CSS selectors and literal sleeps, not the hygiene rules in the author skill.
Apply these minimum cleanups (read the author skill for the full list):
- Wrap actions in
test.describe('<flow>', () => { test('<step>', async ({ page }) => { ... }) })— codegen emits a flat script - Replace CSS selectors with
getByRole/getByLabelwhere the accessible name is unambiguous - Remove any
page.waitForTimeout— replace withexpect(...).toBeVisible()waits against the next stable element - Add at least one
expect()assertion at the end — codegen captures actions, not assertions
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.
- yesterday First seen · 65 lines · 18 tokens per session scan A 65d8ba249f75
record is a command published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 735 once invoked, about $0.0001 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 commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试（支持视频录制、Trace 录制、控制台/网络日志捕获）.
auto-browse
Auto-browse — learn, optimize, and graduate browser operations or web data-mining workflows.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
review
Compare a reference design against an implementation. Accepts Figma URL, image file, or browser URL as reference.
graphify
Turn your vault into a clustered knowledge graph with HTML and JSON outputs.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.