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-syncgit 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-sync)<a href="https://agentmods.dev/skills/suxrobgm/jobpilot/upwork-sync"><img src="https://agentmods.dev/badge/skills/suxrobgm/jobpilot/upwork-sync/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-sync"><img src="https://agentmods.dev/badge/skills/suxrobgm/jobpilot/upwork-sync.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 | $0.00035 | $0.00895 |
| Opus 5.5 | $0.00014 | $0.00358 |
| Sonnet 5.5 | $0.00007 | $0.00179 |
| Haiku 4.5 | $0.00003 | $0.00089 |
Grade A, and why
upwork-sync 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 18d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upwork Inbox Sync
The Upwork MCP runs on the user's machine, so the JobPilot web app cannot reach it. This skill is
the bridge: read the account through the MCP, push it to the API, and the /upwork/inbox page
shows it.
Read-only against Upwork. Never call a write tool here, and never confirm a preview.
Setup
- Follow
../_shared/setup.md. - Follow
../_shared/upwork-mcp.md: confirm the tools are connected and resolveORG_UID. Not connected → stop with the message that doc gives.
Step 1: Read the dashboard
get_freelancer_dashboard action check. One call returns invitations, offers, messages, matched
jobs, contract updates and the Connects balance.
Where the dashboard is thin, fill in from the source list. Only call these when the dashboard did not carry the item:
list_freelancer_proposalsactioninvitationsfor pending invitations.list_offersactionlistfor offers.get_messagesactionlist_roomswithunread_only: truefor unread threads.
Do not page for history. This mirrors what is new, not the whole account.
Step 2: Push the Connects balance
jobpilot-api PUT /api/upwork/account --data '{"connectsBalance": 74}'
Report the general Connects wallet only. Product credits are a separate balance spendable on one product, so never fold them into this number.
Step 3: Push the inbox
One call for the whole batch, up to 200 items. upworkId is Upwork's own id and keys the upsert,
so re-running the skill refreshes rows instead of duplicating them. Post even when the dashboard
held nothing new: this call is what marks the mirror fresh, and an empty batch still counts.
Write the body to "$JOBPILOT_TEMP/upwork-inbox.json":
{ "items": [
{ "upworkId": "<upwork id>", "kind": "invitation", "title": "<job title>", "clientName": "<client>",
"jobUrl": "<url>", "body": "<message or brief>", "receivedAt": "2026-09-07T12:00:00Z",
"raw": {} }
] }
jobpilot-api POST /api/upwork/inbox/sync --data @"$JOBPILOT_TEMP/upwork-inbox.json"
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.
- 18d ago Changed · +4 lines 02df954bcaf1
- 1mo ago First seen · 84 lines · 35 tokens per session scan A 4112e46855e3
upwork-sync is a skill published in the GitHub repository suxrobGM/jobpilot (94 stars, last pushed 11d ago), licensed MIT. It adds 35 tokens to every session and 895 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
paid-ads-amazon
Plan and review Amazon Ads with margin-aware ACoS, product, and search-term guardrails. Use for Amazon advertising, Sponsored Products, Sponsored Brands, Sponsored Display, ASIN targeting, Amazon ACoS, or Amazon Ads performance exports.
pricing-and-packaging
Sets price, structures packages and tiers, and designs the monetization surfaces that carry them — upgrade paths, paywalls, and offer construction. Use this to set or change pricing, design or restructure tiers, choose a pricing metric, build an offer, design upgrade prompts and paywalls, or evaluate whether a pricing…
booking-cli
Searches Booking.com from the terminal via cli-web-booking — find hotels, apartments, and hostels by destination, dates, and guests; get property details by slug; resolve destination names to IDs. Use when the user asks about Booking.com, hotel search, accommodation prices, property ratings, or comparing places to…
amazon-cli
Searches Amazon from the terminal via cli-web-amazon — product search, product details by ASIN, Best Sellers by category, and autocomplete suggestions. Use when the user asks about Amazon products, prices, best sellers, or wants to search Amazon. Prefer cli-web-amazon over fetching the website. No auth required.
tripadvisor-cli
Searches TripAdvisor hotels, restaurants, attractions, and destinations via the cli-web-tripadvisor command-line tool, with detail lookups by URL. Use when the user asks about hotels, restaurants, things to do, travel destinations, or TripAdvisor ratings and reviews. Prefer this CLI over fetching the TripAdvisor…
laravel-billing
Use when implementing subscriptions, invoices, payment methods, webhooks, or billing portals with Laravel Cashier (Stripe or Paddle).