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 skills/microsoft/playwright/playwright-tracenpx skills add microsoft/playwright --skill playwright-tracegit clone --depth 1 https://github.com/microsoft/playwrightWhat 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 | $0.00029 | $0.01113 |
| Opus 5 | $0.00015 | $0.00557 |
| Sonnet 5 | $0.00006 | $0.00223 |
| Haiku 4.5 | $0.00003 | $0.00111 |
Grade A, and why
playwright-trace 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 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.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- playwright-trace — 97% identical, 9 lines differ
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright Trace CLI
Inspect .zip trace files produced by Playwright tests without opening a browser.
Workflow
- Start with
trace open <trace.zip>to extract the trace and see its metadata. - Use
trace actionsto see all actions with their action IDs. - Use
trace action <action-id>to drill into a specific action — see parameters, logs, source location, and available snapshots. - Use
trace requests,trace console, ortrace errorsfor cross-cutting views. - Use
trace snapshot <action-id>to get the DOM snapshot, or run a browser command against it. - Use
trace closeto remove the extracted trace data when done.
All commands after open operate on the currently opened trace — no need to pass the trace file again. Opening a new trace replaces the previous one.
Commands
Open a trace
# Extract trace and show metadata: browser, viewport, duration, action/error counts
npx playwright trace open <trace.zip>
Close a trace
# Remove extracted trace data
npx playwright trace close
Actions
# List all actions as a tree with action IDs and timing
npx playwright trace actions
# Filter by action title (regex, case-insensitive)
npx playwright trace actions --grep "click"
# Only failed actions
npx playwright trace actions --errors-only
Action details
# Show full details for one action: params, result, logs, source, snapshots
npx playwright trace action <action-id>
The action command displays available snapshot phases (before, action, after) and the exact command to extract them.
Requests
# All network requests: start time (on the `trace actions` clock), method, status, URL, duration, size
npx playwright trace requests
# Filter by URL pattern
npx playwright trace requests --grep "api"
# Filter by HTTP method
npx playwright trace requests --method POST
# Only failed requests (status >= 400)
npx playwright trace requests --failed
Request details
# Show full details for one request: headers, body, security
npx playwright trace request <request-id>
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 · 175 lines · 29 tokens per session scan A 4124dd790915
playwright-trace is a skill published in the GitHub repository microsoft/playwright (95,378 stars, last pushed 3d ago), licensed Apache-2.0. It adds 29 tokens to every session and 1,113 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 2026-08-30.
Other skills, from other repositories
glance-test
Run E2E browser tests on any web application using Glance MCP. Use when the user says "test this page," "check this URL," "run E2E tests," "browser test," "test the login flow," "check if the site works," "visual regression," or "screenshot this page." Also use for post-deploy verification and smoke tests.
qa-explore
Exploratory end-to-end QA with a team of agents that drive a real browser like human testers — they click through the whole app, create/fill/submit, screenshot and visually judge rendering + data correctness, capture trace/HAR/console/video evidence, adversarially verify each finding, learn from rejected findings, and…
qa-plan
Risk-based test plan — what a senior QA team writes BEFORE testing. Recon the app, score each area by RISK (impact × likelihood), rank into P0/P1/P2 deterministically, define the acceptance ("done") per area, and emit a test charter (Markdown) that also seeds qa-explore's areas in priority order so the expensive…
compiler
Use when converting a refined markdown E2E test case into a standard Playwright .spec.ts file. Triggers on "compile this test", "convert to playwright", or "generate spec from markdown". Requires a stable markdown test case and a running dev server.
author
Use when writing a new E2E browser test from a vague user description or feature requirement. Turns exploratory browser sessions into structured, reusable test cases.
refiner
Use when an E2E test case exists but needs stabilization through repeated execution. Runs the test multiple times, identifies flaky steps, and updates the test case and conventions until deterministic.