browser-subagent-task-bounding

browser-subagent-task-bounding is a skill for Claude Code from alivirgo/Major-AI-Skills. It costs 29 tokens per session (1,198 once invoked), scanned A, original, MIT.

A method for limiting an automated browser agent to a fixed number of steps, clear stopping rules, and targeted page content.

In plain words
What is it for?
Use it for focused web research, such as finding a rate limit in documentation while extracting only the relevant page elements.
Why use it?
It prevents agents from wandering through irrelevant pages, getting stuck on pop-ups or CAPTCHAs, and collecting far more web content than needed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents; positional $N argument; mentions Codex.

Part of the major-ai-skills plugin — 147 skills, 7 plugins shipped together

Good fit Use it for focused web research, such as finding a rate limit in documentation while extracting only the relevant page elements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alivirgo/major-ai-skills/browser-subagent-task-bounding
Install

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.

Any agent
npx skills add alivirgo/Major-AI-Skills --skill browser-subagent-task-bounding
Clone the repo
git clone --depth 1 https://github.com/alivirgo/Major-AI-Skills

Made for: Claude Code.

Or install major-ai-skills, the plugin that ships this one along with the rest of its 147 skills, 7 plugins.

Wrote 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.

agentmods badge for browser-subagent-task-bounding

README.md
[![agentmods](https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/browser-subagent-task-bounding/github.svg)](https://agentmods.dev/skills/alivirgo/major-ai-skills/browser-subagent-task-bounding)
Your own site
<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.

agentmods 80×15 button for browser-subagent-task-bounding

Your own site · 80×15
<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>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,198 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured today against content hash badeb4d9c98d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

skills/browser-subagent-task-bounding/SKILL.md · 120 lines

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   │
└───────────────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 120 lines

Changes

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.

  1. today Changed · -15 tokens per session badeb4d9c98d
  2. 6d ago First seen · 120 lines · 44 tokens per session scan A e88c34001aa7

Subscribe to this mod's changes

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.

Related

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…

MicrosoftDocs/Agent-Skills · 110 tokens

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…

JohnWayneeee/ai-agent-skills · 96 tokens

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...

rootcastleco/rei-skills · 44 tokens

e2e-automator

Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.

AtulPurohit/Antigravity-Awesome-Skills · 33 tokens

snip

You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.

edouard-claude/snip · 0 tokens

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…

CodeAlive-AI/ai-driven-development · 90 tokens