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/chf3198/copilot-governancenpx agentmods add skills/chf3198/copilot-governance/playwright-vision-low-resourceWrote 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/chf3198/copilot-governance/playwright-vision-low-resource)<a href="https://agentmods.dev/skills/chf3198/copilot-governance/playwright-vision-low-resource"><img src="https://agentmods.dev/badge/skills/chf3198/copilot-governance/playwright-vision-low-resource/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/chf3198/copilot-governance/playwright-vision-low-resource"><img src="https://agentmods.dev/badge/skills/chf3198/copilot-governance/playwright-vision-low-resource.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00062 | $0.02513 |
| Opus 5 | $0.00031 | $0.01256 |
| Sonnet 5 | $0.00012 | $0.00503 |
| Haiku 4.5 | $0.00006 | $0.00251 |
Grade A, and why
playwright-vision-low-resource 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 9d 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright + Vision Low-Resource Profile
Purpose
Stabilize browser automation and visual analysis on low-memory environments without sacrificing verification quality.
This skill is global (user-level) and intended for reuse across all repositories.
Trigger conditions
Use this skill when any of the following apply:
- RAM <= 8 GB total
- Repeated error:
Target page, context or browser has been closed - VS Code extension host instability or OOM events
- Need reliable visual checks with constrained local resources
Hard constraints
- No unbounded retries.
- Max browser-context retries: 2.
- Prefer
workers=1for local runs. - Prefer single-browser project (Chromium) locally.
- Collect heavy artifacts only on failure/retry.
Standard operating profile
1) Environment preflight (always first)
Run:
~/.copilot/skills/playwright-vision-low-resource/scripts/preflight-playwright-mcp.sh
If available memory is low (< 1.5 GB), do not start headed or multi-worker runs.
2) MCP profile (workspace)
For .vscode/mcp.json prefer:
--headless--isolated--no-sandbox- bounded
--timeout-navigationand--timeout-action - file output mode and explicit output dir
Template: ./templates/mcp.low-resource.jsonc
3) Playwright profile (workspace)
For local constrained runs:
workers: 1maxFailures: 1- single local project (
chromium) trace: 'on-first-retry'video: 'retain-on-failure'screenshot: 'only-on-failure'
Template: ./templates/playwright.low-resource.config.ts
4) Vision profile
For Claude vision calls:
- Prefer image long edge <= 1568 px
- Avoid tiny images (< 200 px edge)
- Use 1-3 targeted screenshots per question (not full dumps)
- Prefer viewport/element screenshots over full-page unless layout context is required
5) Failure protocol
If browser-context loss occurs twice in a row:
- Stop browser retries
- Switch to deterministic fallback:
- HTML fetch / DOM inspection
- targeted CSS/JS edits
- CI/quality-gate verification
- Mark visual verification as deferred/manual if required
What ships with it
5 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.
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.
- 9d ago First seen · 292 lines · 62 tokens per session scan A d5172d63ab00
playwright-vision-low-resource is a skill published in the GitHub repository chf3198/copilot-governance (1 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 2,513 once invoked, about $0.0003 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
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…