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 matteotitta/genesys-skills --skill web-task-agentgit clone --depth 1 https://github.com/matteotitta/genesys-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/matteotitta/genesys-skills/web-task-agent)<a href="https://agentmods.dev/skills/matteotitta/genesys-skills/web-task-agent"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/web-task-agent/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/matteotitta/genesys-skills/web-task-agent"><img src="https://agentmods.dev/badge/skills/matteotitta/genesys-skills/web-task-agent.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 | $0.00206 | $0.02224 |
| Opus 5 | $0.00103 | $0.01112 |
| Sonnet 5 | $0.00041 | $0.00445 |
| Haiku 4.5 | $0.00021 | $0.00222 |
Grade A, and why
web-task-agent 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 9d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/web-task-agent — plain-language web task → multi-step loop
Run a web task as a multi-step browser loop on MCPs you already pay for. No new runtime, no API double-billing, no new always-on MCP. Two v1 modes: monitor (watch a page, report a grounded diff) and QA (walk a site, check CTAs/links/schema, flag mismatches).
Provenance
Adapted from browser-use (github.com/browser-use/browser-use, MIT, © 2024 Gregor Zunic) per /steal analysis (2026-06-08) — see .claude/discovery/0626-browser-use-steal-analysis.md. We lift the loop discipline (pre-done verification, soft loop nudges, action chaining, ground-every-claim) as prompt patterns. We do not import the library — the loop runs on Chrome DevTools + Firecrawl MCPs already mounted. That call is the verdict's central KILL: the library duplicates our stack and adds a second Chromium + paid LLM keys.
What this is / is not
A thin orchestration skill: it wraps existing MCPs with a disciplined loop. Client-agnostic — invoke for any engagement or Genesys-internal motion.
| Use this when | Use something else when |
|---|---|
| Watch a page and report what changed | Build/clone a site → /website-build, /website-clone |
| Walk a site checking CTAs / links / schema | One-shot scrape of one URL → Firecrawl directly |
| A repeatable multi-step web task on existing MCPs | LinkedIn engager/profile/job scraping → Apify skills |
| Open-web research → Exa per exa-protocol.md | |
| Form-filling / login-walled automation → deferred to v2 |
Triggers
Invoke when the user says:
/web-task <url> <what to do>- "monitor this page for changes" / "watch this competitor page"
- "QA the CTAs on this site" / "check every link on [url]"
- "check what changed on [url] since last time"
Do NOT invoke when:
- The job is building or cloning a site (
/website-build,/website-clone) - A single
firecrawl_scrapeanswers the question (no loop needed) - The data lives behind a login or needs form submission (v2 — refuse for now, name the reason)
- A pre-built Apify actor already covers the source (LinkedIn, job boards)
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.
- 9d ago First seen · 184 lines · 206 tokens per session scan A 1dc197db35d4
web-task-agent is a skill published in the GitHub repository matteotitta/genesys-skills (36 stars, last pushed 1mo ago), licensed MIT. It adds 206 tokens to every session and 2,224 once invoked, about $0.0010 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
gingiris-b2b-growth
🇺🇸 B2B SaaS Growth — PLG vs SLG Playbook — Diagnose whether your problem is distribution, pricing, or PMF. PLG/SLG selection by ACV and sales cycle, the 5-stage path from $0 to $10M ARR, NRR discipline, affiliate & channel motion, enterprise tiering. Built from HeyGen, Deel, Vercel, Supabase, Snowflake patterns.…
go-to-market-playbook
A reusable Go-to-Market strategy template for both B2B and B2C launches. Covers positioning, messaging, ICP definition, channel selection, and competitive analysis frameworks. By @WeiYipei.
gr-b2b-growth
A guide to growing a business-to-business software product from early user research to large-scale sales. B2B software is sold to companies rather than individual consumers.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
web-browser
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser interaction is required.
browser-skill
Interactive browser automation - navigate, click, type, fill forms, take screenshots, get accessibility snapshots. Supports system Chrome/Edge via auto-detection.