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/wxhou/openspec-playwright/sourcegit clone --depth 1 https://github.com/wxhou/openspec-playwrightWrote 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/wxhou/openspec-playwright/source)<a href="https://agentmods.dev/agents/wxhou/openspec-playwright/source"><img src="https://agentmods.dev/badge/agents/wxhou/openspec-playwright/source.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 | $0.00536 |
| Opus 5 | $0.00000 | $0.00268 |
| Sonnet 5 | $0.00000 | $0.00107 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
SOURCE 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 today.
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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vendored Playwright Agent Snapshots — Provenance
The three agent definition files in claude/ are verbatim snapshots of the
output of Playwright's official agent-initialization CLI. They are redistributed
unmodified (byte-identical); any edit here would break content-based ownership
detection (see openspec/specs/asset-sync/spec.md).
| Field | Value |
|---|---|
| Upstream project | microsoft/playwright |
| Generated by | npx playwright init-agents --loop claude |
| Snapshot baseline | playwright 1.62.1 |
| Files | claude/playwright-test-planner.md, claude/playwright-test-generator.md, claude/playwright-test-healer.md |
| License | Apache-2.0 (© Microsoft Corporation) — https://github.com/microsoft/playwright/blob/main/LICENSE |
The files' tools: frontmatter references mcp__playwright-test__* tools
exposed by the playwright-test MCP server that openspec-pw init installs
(npx playwright run-test-mcp-server). If upstream renames those tools, the
vendored agents fail visibly (MCP tool-call errors), not silently.
Attribution note
Provenance is carried here and in the README rather than inside the agent
files on purpose: a header comment would break YAML frontmatter parsing, and a
trailing comment would break byte-identity with the official CLI output —
byte-identity is what makes content-based ownership (and idempotent
coexistence with user-run init-agents) possible.
Refresh SOP
- Recreate the probe fixture: fresh temp project with
package.json, runnpx playwright init-agents --loop claudewith the target playwright version diffthe produced.claude/agents/playwright-test-*.mdagainsttemplates/agents/claude/- If changed: copy the new files in byte-identically (
cmpmust pass), updatemanifest.json— demote the current hashes intohistoricalHashes(they keep older installs refreshable) and record the new hashes + baseline — then update the baseline version in this table - Frequency: opportunistic — when shipping a release that bumps the playwright baseline, or when a user reports drift; the agents are prompt files, upstream changes are rare
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.
- today First seen · 42 lines · 0 tokens per session scan A 6196594f7440
SOURCE is an agent published in the GitHub repository wxhou/openspec-playwright (10 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 536 tokens. 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 2026-09-05.
Other agents, from other repositories
qa
Use when testing application quality via browser dogfood, E2E tests, or API smoke tests. Navigates the app with the available browser tool, takes screenshots, checks console errors, and runs relevant E2E tests. Read-only — reports issues but never edits code. Also use when the user says 'test this', 'dogfood', 'QA'…
playwright-test-generator
Use this agent to convert a SigNoz E2E test plan into Playwright spec files under tests/e2e/tests/ /. Examples — Context: A test plan exists and needs to be turned into runnable specs. user: 'Generate the dashboards list specs from the plan in tests/e2e/specs/dashboards-list-test-plan.md' assistant: 'Using the…
testing
Agent "testing" from windviki/vBookmarks, covering testing & real-browser harness (detail), unit tests (detail), manual testing checklist and headless smoke test (docker).
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
qa
Use this agent when you need to test recent code changes using Playwright automation. Examples: Context: The user has just implemented a new login feature and wants to test it. user: "I just added a new login validation feature, can you test it?" assistant: "I'll use the qa agent to test your recent changes with…
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.