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-submitgit 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-submit)<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.
<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>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 | $0.00034 | $0.01145 |
| Opus 5.5 | $0.00014 | $0.00458 |
| Sonnet 5.5 | $0.00007 | $0.00229 |
| Haiku 4.5 | $0.00003 | $0.00114 |
Grade A, and why
upwork-submit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 23d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Submit an Upwork Proposal
Take a proposal the user already reviewed in JobPilot and submit it to Upwork. This spends the user's Connects. Never submit without showing the cost and getting an explicit yes in this conversation.
Setup
- Follow
../_shared/setup.md. - Follow
../_shared/upwork-mcp.md: confirm the tools are connected and resolveORG_UID.
Step 1: Load the draft
jobpilot-api GET "/api/upwork/proposals/$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.
list_freelancer_proposalsactioninvitations- is there an invitation for this job?list_freelancer_proposalsactionlist- 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'sjobUrlviafind_jobsactiongetif the id is not already in the brief.cover_letter- the proposal'sproposalText. 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'sscreeningAnswers. The preview lists the job'sscreening_questions; if it asks something the stored answers do not cover, stop and ask the user rather than inventing an answer.
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.
- 23d ago Changed 7835cfdb3063
- 28d ago Changed · -2 lines e7113c71d605
- 1mo ago First seen · 110 lines · 34 tokens per session scan A 31c4e95898a0
upwork-submit is a skill published in the GitHub repository suxrobGM/jobpilot (102 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,145 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-08.
Other skills, from other repositories
update-status
Use when the user reports progress on a role and wants the board updated. Triggers: /update-status, "move X to tech interview", "I got an HR screen with Y", "Z rejected me", "got an offer from W", "schedule my interview with V". Moves a vacancy through the pipeline, appends a timestamped statusDetail (preserving…
promote-idea
Converts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote [idea title]", "turn idea into album", or "start working on [idea]".
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
customer-onboarding-and-implementation
Takes a new customer from signature to working — setting a definition of live that both sides agreed before the contract was signed, planning and staffing the implementation, running data migration and integration realistically, training the people who will actually use it, and handing over to the ongoing…
vendor-management
Selects, contracts, and manages suppliers and vendors — requirements, evaluation, negotiation support, onboarding, performance management, and exit. Use this to choose a vendor, run a selection process, structure a service agreement's operational terms, manage an underperforming supplier, plan an exit or migration, or…
recap-doc
Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…