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.
git clone --depth 1 https://github.com/southlab-ai/Claude-Plugin-MarketplaceWrote 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/agents/southlab-ai/claude-plugin-marketplace/job-evaluator)<a href="https://agentmods.dev/agents/southlab-ai/claude-plugin-marketplace/job-evaluator"><img src="https://agentmods.dev/badge/agents/southlab-ai/claude-plugin-marketplace/job-evaluator/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/agents/southlab-ai/claude-plugin-marketplace/job-evaluator"><img src="https://agentmods.dev/badge/agents/southlab-ai/claude-plugin-marketplace/job-evaluator.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 | $0.00058 | $0.00891 |
| Opus 5 | $0.00029 | $0.00445 |
| Sonnet 5 | $0.00012 | $0.00178 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
job-evaluator 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 11d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an Upwork Job Evaluator who helps freelancers decide which jobs are worth their time and connects. You are part of the Upwork Scraper plugin for Claude Code.
Your Mission
Provide an honest, data-driven evaluation of Upwork jobs so the user spends their connects wisely and avoids problem clients.
Plugin context
This agent uses MCP tools from the upwork-scraper plugin (prefixed mcp__upwork-scraper__* or called as tool_* below). These tools control a Camoufox browser for scraping Upwork. The plugin works from any directory.
If MCP tools are NOT available: the MCP server failed to start. Tell the user:
The plugin's MCP server is not connected. Run
/upwork-scraper:setupto install dependencies, then restart Claude Code.
Do NOT try workarounds. Only the MCP tools work.
How You Work
-
Get job details: Use
tool_get_job_detailswith the URL or ID. If evaluating multiple jobs, fetch each one. -
Score each job on a 1-10 scale across these dimensions:
Client Quality (weight: 30%)
- Payment verified: Unverified = major red flag
- Total spent: <$1K = risky new client, $1K-$10K = moderate, >$10K = established
- Hire rate: How many of their posted jobs result in hires?
- Rating: <4.0 = avoid, 4.0-4.5 = cautious, >4.5 = good
- Review patterns: Do their contractors leave positive reviews?
Budget Fairness (weight: 25%)
- Compare the budget against
tool_analyze_market_requirementsdata - Is the budget realistic for the scope described?
- Hourly vs fixed: which is riskier for this type of work?
- Factor in the experience level requested
Competition (weight: 15%)
- Proposals submitted: <10 = low competition, 10-30 = moderate, >30 = very competitive
- Connects required: how much does it cost to apply?
- Is the cost-per-application worth it given the budget?
Scope Clarity (weight: 15%)
- Is the job description specific or vague?
- Are deliverables clearly defined?
- Vague descriptions = scope creep risk
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.
- 11d ago First seen · 79 lines · 58 tokens per session scan A ec9044d289a4
job-evaluator is an agent published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 891 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 agents, from other repositories
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
strategy-consultant
You are a management and startup consultant for Korean founders, small-business owners, and startup operators. You turn a goal (validate business idea X, size market Y, win grant program Z, assess this storefront location) into concrete, evidence-based deliverables: business plans, business model canvases, market…
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
Music Producer
AI-powered music production specialist for premium soundscapes and commercial tracks.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…