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/njoppi2/playwright-mcp-humanizednpx agentmods add skills/njoppi2/playwright-mcp-humanized/playwright-humanized-linkedinWrote 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/njoppi2/playwright-mcp-humanized/playwright-humanized-linkedin)<a href="https://agentmods.dev/skills/njoppi2/playwright-mcp-humanized/playwright-humanized-linkedin"><img src="https://agentmods.dev/badge/skills/njoppi2/playwright-mcp-humanized/playwright-humanized-linkedin/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/njoppi2/playwright-mcp-humanized/playwright-humanized-linkedin"><img src="https://agentmods.dev/badge/skills/njoppi2/playwright-mcp-humanized/playwright-humanized-linkedin.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 | $0.00038 | $0.00561 |
| Opus 5 | $0.00019 | $0.00280 |
| Sonnet 5 | $0.00008 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade B, and why
playwright-humanized-linkedin scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
If the token is not explicitly provided, extract it from `~/.codex/config.toml`: How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LinkedIn Via Humanized Playwright MCP
Use this skill when the user asks for LinkedIn navigation or LinkedIn task flows through agents.
Mandatory Mode
- For LinkedIn tasks, always use Playwright CLI via
playwright-cli-humanized. - Do not use MCP browser tools (
browser_navigate,browser_click,browser_run_code) for LinkedIn. - If Playwright MCP is configured, ignore it for LinkedIn requests.
Preconditions
- User has Chrome/Edge with Playwright MCP Bridge extension installed.
- User is already logged into LinkedIn in that browser profile.
- MCP server is configured with
playwright-mcp-humanized --extension.
Setup
Generate setup commands:
npx -y playwright-mcp-humanized-agent setup codex
npx -y playwright-mcp-humanized-agent setup claude
npx -y playwright-mcp-humanized-agent setup gemini
For LinkedIn, run Playwright CLI mode from the local repository:
PLAYWRIGHT_MCP_EXTENSION_TOKEN=YOUR_TOKEN \
node ./packages/playwright-mcp/cli-playwright-humanized.js \
open https://www.linkedin.com --extension --headed --browser=chrome
If the token is not explicitly provided, extract it from ~/.codex/config.toml:
PLAYWRIGHT_MCP_EXTENSION_TOKEN="$(
python3 - <<'PY'
import re
from pathlib import Path
text = Path.home().joinpath('.codex/config.toml').read_text()
match = re.search(r'(?m)^\\s*PLAYWRIGHT_MCP_EXTENSION_TOKEN\\s*=\\s*\"([^\"]+)\"\\s*$', text)
print(match.group(1) if match else '', end='')
PY
)" node ./packages/playwright-mcp/cli-playwright-humanized.js \
open https://www.linkedin.com --extension --headed --browser=chrome
Execution Pattern
- Start with read-only navigation tasks (
open profile,collect visible fields,summarize page). - Ask for explicit confirmation before high-impact actions (posting, messaging, invites, submissions).
- Keep interactions paced and limited to user-scoped intent.
Troubleshooting
- If redirected to login, reconnect through extension and verify the active tab/profile.
- If actions fail intermittently, retry with simpler steps and explicit waits.
- If the site challenges the session, reduce action rate and keep manual supervision.
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 · 66 lines · 38 tokens per session scan B 8de42b7a5b77
playwright-humanized-linkedin is a skill published in the GitHub repository njoppi2/playwright-mcp-humanized (2 stars, last pushed 29d ago), licensed Apache-2.0. It adds 38 tokens to every session and 561 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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…