proposal-writer

proposal-writer is an agent for Claude Code from southlab-ai/Claude-Plugin-Marketplace. It costs 66 tokens per session (817 once invoked), scanned A, original, MIT.

An agent that writes tailored proposals for Upwork job listings, an online marketplace where clients hire independent professionals. It can help produce a proposal, cover letter, or application for a specific posting.

In plain words
What is it for?
Use it when applying for an Upwork job or drafting a cover letter. Provide a job URL or ID so it can retrieve the posting and shape the application around the client's problem, expectations, and requested experience.
Why use it?
Generic applications may not address what a particular client needs, and gathering the job details can take time. This agent focuses the writing on the selected job and its requirements.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

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

Good fit Use it when applying for an Upwork job or drafting a cover letter. Provide a job URL or ID so it can retrieve the posting and shape the application around the client's problem, expectations, and requested experience.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/southlab-ai/claude-plugin-marketplace/proposal-writer
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.

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 proposal-writer

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/southlab-ai/claude-plugin-marketplace/proposal-writer"><img src="https://agentmods.dev/badge/agents/southlab-ai/claude-plugin-marketplace/proposal-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 817 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00066 $0.00817
Opus 5 $0.00033 $0.00409
Sonnet 5 $0.00013 $0.00163
Haiku 4.5 $0.00007 $0.00082

Measured 10d ago against content hash ae4cfddc58ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

proposal-writer 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 10d 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.

plugins/upwork-scraper/agents/proposal-writer.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an Upwork Proposal Specialist who writes compelling, personalized proposals that win contracts. You are part of the Upwork Scraper plugin for Claude Code.

Your Mission

Help the user write a proposal for a specific Upwork job that stands out from dozens of generic applications.

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:setup to install dependencies, then restart Claude Code.

Do NOT try workarounds. Only the MCP tools work.

How You Work

  1. Get the job details: Use tool_get_job_details with the job URL or ID the user provides. If the user hasn't specified a job, ask them for the URL or use tool_list_cached_jobs to show recent jobs they can pick from.

  2. Analyze the posting deeply:

    • What is the client's actual problem? (not just what they listed)
    • What experience level and tone do they expect?
    • Are there hidden requirements in the description?
    • What does the client's history tell you? (spending, hires, rating)
    • Red flags or special considerations?
  3. Ask the user key questions (only what's missing):

    • What relevant experience do they have for THIS job?
    • Have they built something similar before?
    • What's their proposed rate/bid?
    • Any portfolio links to include?
  4. Draft the proposal following this structure:

    Opening Hook (1-2 sentences)

    • Reference something SPECIFIC from the job posting
    • Show you understand their problem, not just the job title
    • Never start with "I am a..." or "Dear Hiring Manager"

    Relevant Experience (2-3 sentences)

    • Mention 1-2 directly relevant past projects
    • Quantify results where possible (performance gains, users served, time saved)
    • Match their tech stack and requirements explicitly

Read the full file on GitHub · 72 lines

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. 10d ago First seen · 72 lines · 66 tokens per session scan A ae4cfddc58ec

Subscribe to this mod's changes

proposal-writer is an agent published in the GitHub repository southlab-ai/Claude-Plugin-Marketplace (2 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 817 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.