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 5.5 | $0.00082 | $0.00890 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (46 stars, last pushed 11d ago), licensed MIT. It adds 206 tokens to every session and 2,224 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
yc-jobs-scraper
Scrape daily job listings from YCombinator's Workatastartup platform without duplicates. Use this skill when asked to scrape YC jobs, update the YC companies list, or retrieve the latest startup jobs. It handles authentication, extracts company slugs via Inertia.js JSON payloads, falls back to public YC job pages when…
category-point-of-view
Create a differentiated B2B category point of view that leads with the customer problem, defines the market shift, names the category or strategic frame, and turns it into content, distribution, and measurement guidance.
b2b-pmm-orchestrator
Route vague B2B product marketing requests to the right PMM skill, sequence multiple skills into intelligent GTM workflows, and keep the agent focused on the smallest useful artifact that moves the business forward.
ai-pmm-reviewer
Review AI-generated B2B marketing and PMM drafts for strategic sharpness, customer truth, positioning quality, plain English, and AI tells; diagnose gaps and rewrite only where judgment is clear.
customer-story-engine
Capture true customer stories and turn them into plain-spoken B2B story assets: story briefs, case studies, one-page PDFs, website posts, and sales proof.
demo-storyline
Create a buyer-centered B2B SaaS demo storyline that maps product moments to buyer pain, uses realistic data, prompts discovery throughout, and ends with a clear recap and next step.