best-matches

best-matches is a skill for Claude Code from southlab-ai/Claude-Plugin-Marketplace. It costs 42 tokens per session (433 once invoked), scanned A, original, MIT.

Instructions for fetching a user’s personalized Upwork job recommendations, called Best Matches, through a browser session. Upwork is a freelance-work marketplace.

In plain words
What is it for?
Checking the Upwork session and retrieving the user’s Best Matches or other personalized job recommendations.
Why use it?
They describe how to check authentication, handle login or CAPTCHA steps, fetch recommendations, and report the results when the required tools are available.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions Claude Code.

Part of the upwork-scraper plugin — 4 skills, 5 agents shipped together

Good fit Checking the Upwork session and retrieving the user’s Best Matches or other personalized job recommendations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/southlab-ai/claude-plugin-marketplace/best-matches
Install

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.

Any agent
npx skills add southlab-ai/Claude-Plugin-Marketplace --skill best-matches
Clone the repo
git clone --depth 1 https://github.com/southlab-ai/Claude-Plugin-Marketplace

Made for: Claude Code.

Or install upwork-scraper, the plugin that ships this one along with the rest of its 4 skills, 5 agents.

Wrote 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.

agentmods badge for best-matches

README.md
[![agentmods](https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/best-matches/github.svg)](https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/best-matches)
Your own site
<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/best-matches"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/best-matches/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.

agentmods 80×15 button for best-matches

Your own site · 80×15
<a href="https://agentmods.dev/skills/southlab-ai/claude-plugin-marketplace/best-matches"><img src="https://agentmods.dev/badge/skills/southlab-ai/claude-plugin-marketplace/best-matches.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 433 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.00433
Opus 5 $0.00021 $0.00217
Sonnet 5 $0.00008 $0.00087
Haiku 4.5 $0.00004 $0.00043

Measured 12d ago against content hash 97baac96b4b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

best-matches scanned grade A 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 12d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Do NOT try workarounds (Chrome extension, curl, direct DB access). Only the MCP tools work.
plugins/upwork-scraper/skills/best-matches/SKILL.md · 39 lines

What it actually says

Fetch Upwork Best Matches

Fetch the user's personalized Upwork Best Matches using the MCP tools.

How this plugin works

This plugin provides MCP tools (prefixed mcp__upwork-scraper__* or called as tool_* below) that control a Camoufox browser for scraping Upwork. The plugin works from any directory.

If MCP tools are NOT available (you don't see mcp__upwork-scraper__* in your tools): the MCP server failed to start, likely because dependencies aren't installed. Tell the user:

The plugin's MCP server is not connected. Run /upwork-scraper:setup to install dependencies, then restart Claude Code.

Do NOT try workarounds (Chrome extension, curl, direct DB access). Only the MCP tools work.

Steps

  1. Check session: Call tool_session_status to check if the browser session is authenticated.

    • If state is "active": proceed to step 2.
    • Otherwise: Call tool_start_session(headless=false). A browser window will open. Tell the user to log in to Upwork and solve any CAPTCHAs. When the user confirms, call tool_check_auth to verify.
  2. Fetch jobs: Call tool_fetch_best_matches(max_jobs=$ARGUMENTS or 20, force_refresh=true).

  3. Present results as a clean numbered list with:

    • Job title (bold)
    • Budget / hourly rate
    • Experience level
    • Top 5 skills required
    • Number of proposals
    • URL link
  4. Offer next steps: Ask if they want to:

    • See full details on a specific job
    • Analyze what skills these jobs demand
    • Get portfolio project suggestions based on these jobs
Changes

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.

  1. 12d ago First seen · 39 lines · 42 tokens per session scan A 97baac96b4b5

Subscribe to this mod's changes

best-matches is a skill published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 433 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.