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 alivirgo/Major-AI-Skills --skill browser-subagent-task-boundinggit clone --depth 1 https://github.com/alivirgo/Major-AI-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/alivirgo/major-ai-skills/browser-subagent-task-bounding)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/browser-subagent-task-bounding"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/browser-subagent-task-bounding/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/alivirgo/major-ai-skills/browser-subagent-task-bounding"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/browser-subagent-task-bounding.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 | $0.00029 | $0.01198 |
| Opus 5 | $0.00015 | $0.00599 |
| Sonnet 5 | $0.00006 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
browser-subagent-task-bounding 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 today.
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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bounded Browser Subagent Execution (Loop & DOM Bounding)
Overview
Spawning an autonomous browser subagent with a vague prompt ("Go to the documentation website and find information on rate limits") is one of the most expensive failure modes in agentic systems.
Unbounded browser subagents click exploratory links, get trapped in cookie banners and CAPTCHAs, ingest raw 50,000-token HTML DOM trees, and take 30+ visual screenshots - burning 200,000+ tokens and stalling the parent agent for 5 minutes.
The Bounded Browser Subagent Protocol enforces strict Step Ceilings, Deterministic Stop Conditions, and Selector-Targeted DOM Extractions.
Unbounded Exploration vs. Bounded Surgical Execution
┌─────────────────────────────────────────────────────────────┐
│ Browser Subagent Execution │
│ │
│ Unbounded Browser Subagent (Anti-Pattern): │
│ • Prompt: "Find rate limits on Stripe docs" │
│ • Navigates 8 pages, clicks blog links, accepts cookies │
│ • Dumps entire HTML body (45,000 tokens) on each step │
│ • 28 Steps executed, $2.40 billed, 4 minutes elapsed │
│ │
│ Bounded Surgical Subagent Protocol: │
│ • Target URL: `https://docs.stripe.com/rate-limits` │
│ • Max Steps: 3 │
│ • Stop Condition: Read `#rate-limits-table` $\rightarrow$ Return TSV│
│ • 2 Steps executed, $0.04 billed, 6 seconds elapsed │
└─────────────────────────────────────────────────────────────┘
The 4 Bounding Pillars
Every invocation of browser_subagent must define these 4 explicit boundaries:
┌───────────────────────────────────────────────────────────────────────────┐
│ 1. DIRECT TARGET URL: Direct deep-link; never start on a generic homepage │
│ 2. HARD STEP CEILING: Maximum 5 to 8 actions before forced return │
│ 3. DETERMINISTIC STOP: "Stop immediately when element [X] is visible" │
│ 4. STRICT RETURN SCHEMA: Return only a compact JSON object or TSV table │
└───────────────────────────────────────────────────────────────────────────┘
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.
- today Changed · -15 tokens per session badeb4d9c98d
- 6d ago First seen · 120 lines · 44 tokens per session scan A e88c34001aa7
browser-subagent-task-bounding is a skill published in the GitHub repository alivirgo/Major-AI-Skills (1 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 1,198 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
azure-playwright-workspaces
Expert knowledge for Playwright Workspaces development including troubleshooting, best practices, decision making, limits & quotas, security, and configuration. Use when managing Playwright Testing workspaces, tokens/RBAC, quotas, monitoring/metrics, or run/AADSTS7000112 issues, and other Playwright Workspaces related…
browser-audit
Run a pre-deploy browser audit of a live, preview, or local web page for accessibility, SEO, Lighthouse quality, and critical UX issues. Use when asked to audit a page/site before deployment, check WCAG 2.2 AA, WAI-ARIA, Lighthouse, accessibility, SEO, contrast, keyboard navigation, focus states, semantic HTML, forms…
azure-microsoft-playwright-testing-ts
Run Playwright tests at scale using Azure Playwright Workspaces (formerly Microsoft Playwright Testing). Use when scaling browser tests across cloud-hosted browsers, integrating with CI/CD pipeline...
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
fetch-url-as-markdown
Fetch a web page (URL) and return clean Markdown via local trafilatura, with Exa MCP as a fallback for JS-rendered or anti-bot pages. Use when the user asks to read, fetch, scrape, summarize, or quote a URL — prefer this over the built-in WebFetch tool. Don't use for binary files (PDFs, images, archives) or for…