What is advanced-web-search?

A web-search skill that finds and ranks candidate sources using targeted queries and search operators such as site and filetype filters.

Discovering official docs, research papers, code repositories, recent posts, and competing or risk-related evidence.

It reduces the time spent finding reliable documentation, papers, repositories, and other relevant sources.

advanced-web-search — Skill for Codex by keysersoose

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 keysersoose/claude-code-setup --skill advanced-web-search

Clone the repo

git clone --depth 1 https://github.com/keysersoose/claude-code-setup

Made for: Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/keysersoose/claude-code-setup/advanced-web-search.svg)](https://agentmods.dev/skills/keysersoose/claude-code-setup/advanced-web-search)

Your own site

<a href="https://agentmods.dev/skills/keysersoose/claude-code-setup/advanced-web-search"><img src="https://agentmods.dev/badge/skills/keysersoose/claude-code-setup/advanced-web-search.svg" alt="Measured on agentmods" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,773 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.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.01773
Opus 5	$0.00041	$0.00886
Sonnet 5	$0.00016	$0.00355
Haiku 4.5	$0.00008	$0.00177

Measured 6d ago against content hash fe680f6bc55d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

advanced-web-search 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 6d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/__init__.py, scripts/google_opencli_x_search.py, scripts/opencli_api_paginate.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/advanced-web-search/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Advanced Web Search

Overview

Use this skill to discover high-quality candidate sources. Use the bundled OpenCLI Google backend by default for repeatable Google-operator discovery and saved JSON output. Other search, browser, HTTP, API, terminal, or MCP tools are fallbacks or verification aids. Search results are discovery leads, not evidence.

Core Workflow

Clarify the search target, constraints, freshness needs, and source classes.
Build several targeted query classes instead of one broad query.
Use search operators where supported: site:, filetype:, after:, before:, quoted phrases, boolean OR, exclusions, intitle:, inurl:, and intext:.
Run broad, primary-source, technical/paper/code, community, risk/counter-evidence, and recent-update queries as relevant.
Triage candidate URLs by source type, credibility, relevance, date, and extraction feasibility.
Hand off the selected source list to direct fetching, crawling, browser inspection, or the deep-research skill if synthesis is needed.

Required Search Tool

For repeatable source discovery, use the OpenCLI Google backend by default. Do not use a harness built-in web search as the primary discovery step for deep research when this script is available. Do not rely on terminal JSON redirection; always pass --output <path> so the result file is UTF-8 JSON and can be handed to deep-research.

python scripts/opencli_google_search.py \
  --query "Hermes Agent NousResearch site:github.com" \
  --max-results 20 \
  --pages 6 \
  --output outputs/hermes_agent_sources.json

Files:

scripts/opencli_google_search.py - default Advanced Web Search backend. It uses OpenCLI's browser bridge to render Google in Chrome, supports Google operators and start= pagination, deduplicates canonical URLs, and writes clean JSON for any website with best-effort site metadata for common social, news, code, official, and research domains.
scripts/opencli_network_probe.py - optional: scores likely JSON/list endpoints behind a dynamic page. Usage in references/dynamic-page-loading.md.
scripts/opencli_api_paginate.py - optional: paginates a probe-found JSON endpoint in Chrome with cookies. Usage in references/dynamic-page-loading.md.
scripts/google_opencli_x_search.py - Google result pagination through OpenCLI's logged-in Chrome bridge for X/Twitter result discovery. Use when raw Google HTML is blocked or when you need clean X post JSON with canonical URL, title, approximate likes, and X snowflake timestamp.
scripts/operator_registry.py - operator parsing, validation, and query construction.
scripts/test_opencli_google_search.py - offline tests for the default OpenCLI Google backend.

Read the full file on GitHub · 137 lines

Files

What ships with it

12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

6d ago First seen · 137 lines · 82 tokens per session scan A fe680f6bc55d

Subscribe to this mod's changes

advanced-web-search is a skill published in the GitHub repository keysersoose/claude-code-setup (2 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 1,773 once invoked, about $0.0004 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 2026-08-31.

Research

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens