upwork-submit

upwork-submit is a skill for Claude Code from suxrobGM/jobpilot. It costs 34 tokens per session (1,258 once invoked), scanned A, original, MIT.

A tool for sending an already approved proposal to Upwork, an online marketplace for freelance work. It checks that the proposal is still a draft and requires the user to approve the Connects cost before sending.

In plain words
What is it for?
It is for submitting a reviewed JobPilot proposal to an Upwork job. It is not for writing the proposal or submitting one that has already been sent.
Why use it?
It prevents accidental duplicate submissions and stops the agent from spending Upwork application credits without clear permission. It also checks for existing invitations or applications first.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the jobpilot plugin — 22 skills, 2 agents, 2 MCP servers shipped together

Good fit It is for submitting a reviewed JobPilot proposal to an Upwork job. It is not for writing the proposal or submitting one that has already been sent.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/suxrobgm/jobpilot/upwork-submit
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 suxrobGM/jobpilot --skill upwork-submit
Clone the repo
git clone --depth 1 https://github.com/suxrobGM/jobpilot

Made for: Claude Code.

Or install jobpilot, the plugin that ships this one along with the rest of its 22 skills, 2 agents, 2 MCP servers.

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 upwork-submit

README.md
[![agentmods](https://agentmods.dev/badge/skills/suxrobgm/jobpilot/upwork-submit/github.svg)](https://agentmods.dev/skills/suxrobgm/jobpilot/upwork-submit)
Your own site
<a href="https://agentmods.dev/skills/suxrobgm/jobpilot/upwork-submit"><img src="https://agentmods.dev/badge/skills/suxrobgm/jobpilot/upwork-submit/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 upwork-submit

Your own site · 80×15
<a href="https://agentmods.dev/skills/suxrobgm/jobpilot/upwork-submit"><img src="https://agentmods.dev/badge/skills/suxrobgm/jobpilot/upwork-submit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,258 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 $0.00034 $0.01258
Opus 5 $0.00017 $0.00629
Sonnet 5 $0.00007 $0.00252
Haiku 4.5 $0.00003 $0.00126

Measured yesterday against content hash 31c4e95898a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

upwork-submit 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 yesterday.

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.

PROPOSAL=$(curl -fsS -H "authorization: Bearer $JOBPILOT_API_TOKEN" "$JOBPILOT_API/api/upwork/proposals/$ARG")
plugin/skills/upwork-submit/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Submit an Upwork Proposal

Take a proposal the user already reviewed in JobPilot and submit it to Upwork. This spends the user's Connects. Never submit without showing the cost and getting an explicit yes in this conversation.

Setup

  1. Follow ../_shared/setup.md.
  2. Follow ../_shared/upwork-mcp.md: confirm the tools are connected and resolve ORG_UID.

Step 1: Load the draft

PROPOSAL=$(curl -fsS -H "authorization: Bearer $JOBPILOT_API_TOKEN" "$JOBPILOT_API/api/upwork/proposals/$ARG")

Require .status == "draft". Anything else → stop and say what the status is; a submitted proposal must not be sent twice.

Require a non-empty .proposalText and a .jobUrl. Missing either → tell the user to draft it first with the upwork-proposal skill, then stop.

Step 2: Check for an existing invitation or proposal

Mandatory. Never skip. Upwork rejects a create on a job the user was invited to or already applied to, with error VJ-JA-10, and the turn is wasted.

  1. list_freelancer_proposals action invitations - is there an invitation for this job?
  2. list_freelancer_proposals action list - is there already a proposal for it?

An existing proposal → stop and tell the user; do not submit again. An invitation → use manage_proposals action accept_invitation with the invitation's id instead of create, and confirm with type proposal_accept_invitation.

Step 3: Build the preview

manage_proposals action create with:

  • job_reference - the numeric job id, not the ~02… ciphertext. Resolve it from the proposal's jobUrl via find_jobs action get if the id is not already in the digest.
  • cover_letter - the proposal's proposalText. Max 5000 characters; if it is longer, stop and ask the user to shorten it rather than truncating their words.
  • charged_amount - the bid, as a number.
  • answers - the proposal's screeningAnswers. The preview lists the job's screening_questions; if it asks something the stored answers do not cover, stop and ask the user rather than inventing an answer.

Read the full file on GitHub · 110 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. yesterday First seen · 110 lines · 34 tokens per session scan A 31c4e95898a0

Subscribe to this mod's changes

upwork-submit is a skill published in the GitHub repository suxrobGM/jobpilot (66 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 1,258 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 2026-09-08.

Related

Other skills, from other repositories

work

Execute Elixir/Phoenix plan tasks with progress tracking. Use after /phx:plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.

oliver-kriska/claude-elixir-phoenix · 43 tokens

catchup

Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.

oliver-kriska/claude-elixir-phoenix · 48 tokens

plan

Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.

oliver-kriska/claude-elixir-phoenix · 42 tokens

phx-deps-update

Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).

oliver-kriska/claude-elixir-phoenix · 62 tokens

project-update

Update project configuration to match the latest HCF plugin defaults. Use when the HCF plugin has been updated and you want to sync your project's config.

markshust/hcf · 33 tokens

sync-project-docs

Usar para sincronizar la documentación viva del proyecto después de una fase. También: actualizar docs/project, índice, architecture.md, compliance.md, threat-model.

686f6c61/alfred-dev · 37 tokens