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 abullaisi/upwork-skills --skill upwork-client-messengergit clone --depth 1 https://github.com/abullaisi/upwork-skillsWrote 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/abullaisi/upwork-skills/upwork-client-messenger)<a href="https://agentmods.dev/skills/abullaisi/upwork-skills/upwork-client-messenger"><img src="https://agentmods.dev/badge/skills/abullaisi/upwork-skills/upwork-client-messenger/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/abullaisi/upwork-skills/upwork-client-messenger"><img src="https://agentmods.dev/badge/skills/abullaisi/upwork-skills/upwork-client-messenger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00125 | $0.01524 |
| Opus 5 | $0.00063 | $0.00762 |
| Sonnet 5 | $0.00025 | $0.00305 |
| Haiku 4.5 | $0.00013 | $0.00152 |
Grade A, and why
upwork-client-messenger 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upwork Client Messenger
Mid-contract messages decide whether a contract ends in a review and a referral or in silence. Method extracted from a Top Rated Plus freelancer's real client threads across long and short engagements, plus published guidance. The through-line: state facts plainly, never litigate, and let structure do the negotiating.
Inputs
- The situation (which of the five below).
- Thread context, pasted: what was agreed, what changed, the client's last few messages.
- Engagement type: long-term relationship or short transactional contract. Several moves below fork on this; ask if unclear. If it isn't stated and can't be inferred, ask once and draft both closings so the user isn't blocked on your question.
Profile shortcut: if a stored profile file exists (upwork-profile.md in the working directory or ~/.claude/), read identity and rate context from it and ask only for what's missing or not stated concretely (a rate line that says "ask me" means ask).
Voice (hard, applies to all five)
Professional peer, warm and short. Contractions, plain words, no em dashes. Banned: permission-seeking and apology stacking. "Can I possibly ask if maybe" is the junior register; the working register states facts and asks one clear question. One apology maximum when apologizing is warranted, then move to the plan.
1. Delay news
Lead with the revised date in the first line; never bury it under context. Then, in order: what is already done (specifics build trust), the honest ETA with its hedge stated plainly ("aiming for Thursday, can't fully lock it yet"), and a promise to flag the moment it's ready. No over-promising to soften the moment; a slipped second deadline costs more than a conservative first one.
When the delay is the client's, zero pushback: well wishes, confirm no rush. Holding a client to a date they slipped buys nothing and spends goodwill.
2. Scope creep (the fork that matters most)
First, classify with the repeated-game rule:
- First small extra ask from a good long-term client: do it, and name it as a courtesy in the same message ("happy to include this one; it sits outside our original scope, so flagging it"). The boundary is set without a confrontation.
- Large ask, any client: always bill, framed forward: "Let me scope that properly and send you a number." Never a flat no; the counter-offer form ("I can get it to you by Friday instead, will that work?") declines the terms while accepting the relationship.
- Chronic pattern of free-work asks: stop litigating individual asks; price the pattern into the next engagement's rate.
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.
- 10d ago First seen · 75 lines · 125 tokens per session scan A 764f097893d6
upwork-client-messenger is a skill published in the GitHub repository abullaisi/upwork-skills (100 stars, last pushed 1mo ago), licensed MIT. It adds 125 tokens to every session and 1,524 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
apollo-lead-finder
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…