Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/WackyGem/Fleurnpx agentmods add skills/wackygem/fleur/fleur-playwright-cdp-debugWrote 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/wackygem/fleur/fleur-playwright-cdp-debug)<a href="https://agentmods.dev/skills/wackygem/fleur/fleur-playwright-cdp-debug"><img src="https://agentmods.dev/badge/skills/wackygem/fleur/fleur-playwright-cdp-debug/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/skills/wackygem/fleur/fleur-playwright-cdp-debug"><img src="https://agentmods.dev/badge/skills/wackygem/fleur/fleur-playwright-cdp-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00105 | $0.00859 |
| Opus 5.5 | $0.00042 | $0.00344 |
| Sonnet 5.5 | $0.00021 | $0.00172 |
| Haiku 4.5 | $0.00011 | $0.00086 |
Grade A, and why
fleur-playwright-cdp-debug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright CDP Frontend Debug
Overview
Use this skill for exploratory frontend debugging in fleur through an existing Chromium browser exposed by vnc-mini-desktop over Chrome DevTools Protocol.
This repo skill is a thin fleur wrapper. Prefer the official playwright-cli skill for detailed command semantics when it is installed; use this skill for project defaults, endpoint checks, and safe workflow boundaries.
Defaults
- Global CLI package:
@playwright/cli - CLI command:
playwright-cli - Official skill install command:
playwright-cli install --skills agents - CDP env var:
PLAYWRIGHT_CDP_ENDPOINT - Default CDP endpoint:
http://127.0.0.1:9222 - CDP health check:
node scripts/check_playwright_cdp.mjs - Browser owner: Docker
vnc-mini-desktop; do not close this browser unless explicitly asked. - Default Playwright CLI entrypoint:
playwright-cli attach --cdp="${PLAYWRIGHT_CDP_ENDPOINT:-http://127.0.0.1:9222}"; do not useplaywright-cli openfor this repo workflow.
Workflow
- Start the frontend dev server if the page requires one.
- Verify the CDP endpoint:
node scripts/check_playwright_cdp.mjs
- Attach to the existing browser:
playwright-cli attach --cdp="${PLAYWRIGHT_CDP_ENDPOINT:-http://127.0.0.1:9222}"
- Navigate and inspect:
playwright-cli goto http://127.0.0.1:<port>
playwright-cli snapshot
playwright-cli console
playwright-cli requests
playwright-cli screenshot
- Check responsive layouts with stable viewport sizes:
playwright-cli resize 1440 900
playwright-cli screenshot
playwright-cli resize 390 844
playwright-cli screenshot
- Detach when finished:
playwright-cli detach
Guidance
- Use CDP debugging for exploratory UI inspection, screenshots, console/network diagnostics, and reproducing user-visible issues.
- Use deterministic Playwright tests for CI-grade assertions; CDP attachment is lower fidelity than Playwright's native protocol and is Chromium-only.
- Do not rely on local browser downloads or system Chrome for this workflow. The target browser is the existing CDP browser in
vnc-mini-desktop. - Do not start a new browser with
playwright-cli openunless the user explicitly asks for an isolated local browser session. - Do not use
playwright-cli closeagainst the external VNC browser unless the user explicitly asks to shut it down. - If
playwright-cli install --skills agentsretries browser downloads and the official skill directory already exists, it is acceptable to stop the download; CDP debugging can still work.
What ships with it
1 file 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.
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 · 80 lines · 105 tokens per session scan A b5b40ca1176c
fleur-playwright-cdp-debug is a skill published in the GitHub repository WackyGem/Fleur (138 stars, last pushed 15d ago), licensed MIT. It adds 105 tokens to every session and 859 once invoked, about $0.0004 per session on Opus 5.5. 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
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
chrome-performance-optimizer
Autonomous multi-agent performance optimization loop for Chromium and V8. Supports profile-seeded mode (analyzing Speedometer 3 / JetStream profiles via pprof or Sagacity MCP) and pattern-driven discovery mode (fan-out exploration of Blink and V8 macro-patterns grounded in historical wins and past rejected CLs).…
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.