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/jpbaking/playwright-fieldkit/pw-playwright-fieldkitnpx skills add jpbaking/playwright-fieldkit --skill pw-playwright-fieldkitgit clone --depth 1 https://github.com/jpbaking/playwright-fieldkitWrote 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/skills/jpbaking/playwright-fieldkit/pw-playwright-fieldkit)<a href="https://agentmods.dev/skills/jpbaking/playwright-fieldkit/pw-playwright-fieldkit"><img src="https://agentmods.dev/badge/skills/jpbaking/playwright-fieldkit/pw-playwright-fieldkit.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 | $0.00143 | $0.01492 |
| Opus 5 | $0.00072 | $0.00746 |
| Sonnet 5 | $0.00029 | $0.00298 |
| Haiku 4.5 | $0.00014 | $0.00149 |
Grade A, and why
pw-playwright-fieldkit 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 5d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PW Playwright FieldKit
Drive the bundled scripts and reason over their reports. Do not improvise raw Playwright code for operations already supported here.
Package paths
The scripts have one runtime home, the user-global skill root (installed for every harness; if this SKILL.md was discovered elsewhere, still run the scripts from here):
~/.agents/skills/pw-playwright-fieldkit
Run tools from the project/workspace root so reports land in the project, for example:
node ~/.agents/skills/pw-playwright-fieldkit/scripts/crawl.mjs <URL> --out report/explore
Install the runtime dependencies once per machine if needed:
(cd ~/.agents/skills/pw-playwright-fieldkit/scripts && npm ci && npx playwright install chromium)
Route the request
Read and follow exactly one primary workflow. Read another only when the task genuinely crosses intents.
- Explore, map, health-check, or understand a site: pw-explore-site
- Reproduce a bug or diagnose wrong navigation: pw-debug-site
- Find undocumented, authenticated, or role-gated functionality: pw-discover-features
- Derive traceable draft test cases from a feature specification: pw-design-test-cases
- Review and explicitly approve specification-derived test cases: pw-review-test-cases
- Derive candidate journeys by reading the application's routing/handler source, reconciled against a crawl: pw-derive-tests-from-code
- Turn a confirmed journey into a permanent traced test: pw-generate-tests
- Record a journey demonstrated interactively by the user: pw-record-flow
- Execute an approved test-case document as a journey, capture a trace, and request confirmation: pw-execute-test-case
- Run existing permanent automated tests without changing them and report all traces: pw-run-automated-tests
- Capture intent, risk, data, outcomes, and cleanup: pw-create-test-charter
- Find crawl routes/forms without test evidence: pw-analyze-test-coverage
- Plan isolated setup and idempotent cleanup: pw-plan-test-data
- Run meaningful role/browser/device variants: pw-run-test-matrix
- Add deterministic API failure and boundary paths: pw-generate-negative-tests
- Audit accessibility after interactive state changes: pw-audit-journey
- Reproduce and classify intermittent failures: pw-triage-flaky-test
- Audit reliability, accessibility, performance, UX, or testability: pw-recommend-improvements
- Compare before/after, anonymous/authenticated, or role-based crawls: pw-compare-runs
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 229 B
- references/workflows/pw-analyze-test-coverage.md 1.2 KB
- references/workflows/pw-audit-journey.md 946 B
- references/workflows/pw-compare-runs.md 2.5 KB
- references/workflows/pw-create-test-charter.md 960 B
- references/workflows/pw-debug-site.md 5.0 KB
- references/workflows/pw-derive-tests-from-code.md 12 KB
- references/workflows/pw-design-test-cases.md 3.3 KB
- references/workflows/pw-discover-features.md 3.0 KB
- references/workflows/pw-execute-test-case.md 7.8 KB
- references/workflows/pw-explore-site.md 2.8 KB
- references/workflows/pw-generate-negative-tests.md 1.1 KB
- references/workflows/pw-generate-tests.md 4.6 KB
- references/workflows/pw-plan-test-data.md 950 B
- references/workflows/pw-recommend-improvements.md 2.5 KB
- references/workflows/pw-record-flow.md 4.2 KB
- references/workflows/pw-review-test-cases.md 3.5 KB
- references/workflows/pw-run-automated-tests.md 3.9 KB
- references/workflows/pw-run-test-matrix.md 1.3 KB
- references/workflows/pw-triage-flaky-test.md 1.0 KB
- scripts/charter.mjs 4.3 KB runs code
- scripts/compare.mjs 8.1 KB runs code
- scripts/coverage.mjs 6.8 KB runs code
- scripts/crawl.mjs 13 KB runs code
- scripts/flow.mjs 8.4 KB runs code
- scripts/inspect.mjs 8.2 KB runs code
- scripts/lib/audit.mjs 5.5 KB runs code
- scripts/lib/browser.mjs 4.4 KB runs code
- scripts/lib/extract.mjs 7.2 KB runs code
- scripts/lib/flow-actions.mjs 768 B runs code
- scripts/lib/gen-test.mjs 9.6 KB runs code
- scripts/lib/instrument.mjs 3.3 KB runs code
- scripts/lib/links.mjs 4.0 KB runs code
- scripts/lib/reporter.mjs 9.1 KB runs code
- scripts/lib/run-step.mjs 6.5 KB runs code
- scripts/lib/scope.mjs 2.6 KB runs code
- scripts/lib/sitemap.mjs 5.8 KB runs code
- scripts/lib/spa.mjs 3.5 KB runs code
- scripts/lib/state-audit.mjs 3.4 KB runs code
- scripts/lib/util.mjs 5.1 KB runs code
- scripts/matrix.mjs 3.5 KB runs code
- scripts/package-lock.json 2.2 KB
- scripts/package.json 1.3 KB
- scripts/record.mjs 6.0 KB runs code
- scripts/save-auth.mjs 3.5 KB runs code
- scripts/test-cases.mjs 13 KB runs code
- scripts/test/fixture/about.html 194 B
- scripts/test/fixture/added.html 162 B
- scripts/test/fixture/final-target.html 170 B
- scripts/test/fixture/flaky-command.mjs 389 B runs code
- scripts/test/fixture/flow.html 654 B
- scripts/test/fixture/flow.json 794 B
- scripts/test/fixture/index-baseline.html 922 B
- scripts/test/fixture/index-current.html 1.1 KB
- scripts/test/fixture/inspect.html 368 B
- scripts/test/fixture/private.html 184 B
- scripts/test/fixture/removed.html 232 B
- scripts/test/fixture/robots.txt 70 B
- scripts/test/fixture/sitemap-only.html 178 B
- scripts/test/fixture/sitemap.xml 163 B
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.
- 5d ago First seen · 111 lines · 143 tokens per session scan A 8c047bbb55df
pw-playwright-fieldkit is a skill published in the GitHub repository jpbaking/playwright-fieldkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 143 tokens to every session and 1,492 once invoked, about $0.0007 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 skills, from other repositories
qawolf-cli
Manage QA Wolf through the qawolf CLI. Use when asked to create, update, or list coverage requests, bug reports, or maintenance reports; start a run of flows or tags on the QA Wolf platform or read a run's results; list, set, or delete environment variables; manage environments, flows, or tags; request automation of…
playwright-expert
Expert in Playwright E2E testing framework, auto-waiting mechanisms, test generation, trace viewer, and CI/CD integration. Use when the user mentions testing, end-to-end tests, QA, automation, end-to-end testing, or test automation, or when the task involves Playwright Framework, Test Organization, Advanced Features…
e2e-setup
Set up Playwright e2e automation tailored to this team and app. Probes the running app (auth mechanism, API surface, spec availability), interviews with recommendations instead of open questions, scaffolds the playwright/ folder, and records every decision in playwright/AUTOMATION.md for the other e2e skills to read.…
verify-fix
Re-test a bug fix after a developer resolves it. Pulls the original bug from Jira, re-executes the repro steps in the browser, checks for regressions, and updates the bug status. The final step in the SDT workflow before a ticket moves to Done. Use when: "verify fix", "retest", "is this fixed?", "check BUG-123"…
browser-test-executor
Execute approved bounded browser Test DSL cases with fresh isolated contexts and auditable attempts. Use when running browser tests, reruns, regression checks, or blocked execution diagnostics.
playwright-test
Run end-to-end browser tests using the Playwright Test CLI. Create test configs, write spec files with expect assertions, execute tests with npx playwright test, and analyze results. Pre-installed with Chromium in the computer image — no setup needed. Use for E2E testing, regression testing, smoke tests, visual…