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.
npx skills add suxrobGM/jobpilot --skill upwork-proposalgit clone --depth 1 https://github.com/suxrobGM/jobpilotWrote 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/suxrobgm/jobpilot/upwork-proposal)<a href="https://agentmods.dev/skills/suxrobgm/jobpilot/upwork-proposal"><img src="https://agentmods.dev/badge/skills/suxrobgm/jobpilot/upwork-proposal.svg" alt="Measured on agentmods" 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 | $0.00028 | $0.01595 |
| Opus 5 | $0.00014 | $0.00797 |
| Sonnet 5 | $0.00006 | $0.00319 |
| Haiku 4.5 | $0.00003 | $0.00160 |
Grade A, and why
upwork-proposal 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 7d 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.
curl -fsS -H "authorization: Bearer $JOBPILOT_API_TOKEN" "$JOBPILOT_API/api/upwork/proposals/$ARG" How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upwork Proposal Generator
Write a concise, winning Upwork proposal that directly addresses the client's needs. Clients skim proposals on mobile, between meetings - if it takes more than ~30 seconds to read, it's gone. Optimize every line for a fast skim.
Setup
Follow ../_shared/setup.md. Then Read the resume at primaryResumeSourceAbsolutePath for full context (identity, skills, experience, projects, research).
Step 1: Resolve the Input
The argument is either a proposal id (an integer, when launched from the JobPilot UI) or a raw job description (manual use). Detect which:
-
Integer id → fetch the draft row and use its stored job details as the JD:
curl -fsS -H "authorization: Bearer $JOBPILOT_API_TOKEN" "$JOBPILOT_API/api/upwork/proposals/$ARG"Use
jobDescriptionas the posting, plusjobTitle/clientName/jobUrlfor context. Remember the id - you willPATCHthe result back to it in Step 7. (A draft launched from an Upwork search recommendation already has these fields filled andsource:"search"- same flow, no extra work.) -
Anything else → treat the argument itself as the job description. There is no row yet; you will
POSTa new one in Step 7.
Step 2: Analyze the JD
Identify: what the client needs built/fixed, required tech and skills, scope and timeline clues, pain points/challenges, and any specific questions the client asks. Pull out one concrete detail unique to this posting - you'll reference it in the hook so the client can tell the proposal isn't a mass send.
Step 3: Select ONE Matching Case Study
Pick the SINGLE most relevant project from the resume - one that matches their problem, not just their tech stack. One specific, on-point case study beats five generic ones. Don't list everything. If a portfolio/GitHub/live link exists for it, keep that link ready.
Step 4: Write
Order it the way it gets read - them first, you second, never the reverse.
Hook (line 1, bolded): Open with a bold line that names their problem or goal in their words. Upwork renders **text** as bold - use it on this line so it stands out instantly. This is the single most important line; if it reads like "Hello, I'm excited to apply," the proposal is deleted. No "Hi" / "Dear client" / "I'm excited to apply" / "I came across your posting."
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.
- 7d ago First seen · 99 lines · 28 tokens per session scan A af73f7966dd6
upwork-proposal is a skill published in the GitHub repository suxrobGM/jobpilot (65 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 1,595 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
security
Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.