web-research

web-research is a skill for Claude Code from GoogilyBoogily/googilyboogily-claude-power-tools. It costs 55 tokens per session (1,414 once invoked), scanned A, original, MIT.

A research workflow for finding and organizing outside technical information, such as official SDK documentation, API references, standards, issue discussions, and implementation examples. It produces a structured report with sources.

In plain words
What is it for?
Use it when choosing an integration approach, checking an API or SDK, investigating a technical issue, comparing implementations, or verifying a best practice or standard.
Why use it?
It reduces the time spent searching scattered technical information and helps validate design choices with traceable evidence. If one research source is unavailable, it can try other source types.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the architecture-docs plugin — 19 skills shipped together

Good fit Use it when choosing an integration approach, checking an API or SDK, investigating a technical issue, comparing implementations, or verifying a best practice or standard.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/googilyboogily/googilyboogily-claude-power-tools/web-research
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 GoogilyBoogily/googilyboogily-claude-power-tools --skill web-research
Clone the repo
git clone --depth 1 https://github.com/GoogilyBoogily/googilyboogily-claude-power-tools

Made for: Claude Code.

Or install architecture-docs, the plugin that ships this one along with the rest of its 19 skills.

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 web-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/web-research/github.svg)](https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/web-research)
Your own site
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/web-research"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/web-research/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 web-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/googilyboogily/googilyboogily-claude-power-tools/web-research"><img src="https://agentmods.dev/badge/skills/googilyboogily/googilyboogily-claude-power-tools/web-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,414 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 $0.00055 $0.01414
Opus 5 $0.00028 $0.00707
Sonnet 5 $0.00011 $0.00283
Haiku 4.5 $0.00006 $0.00141

Measured 12d ago against content hash c994a6fe9ccc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

web-research 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 12d 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.

plugins/architecture-docs/skills/web-research/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Researcher

You are a systematic external knowledge researcher. Your job is to answer a research question using web sources and produce a structured, citable report.

Input

The user provides a research question or topic, e.g.:

  • "What are best practices for PayPal SDK v6 integration patterns?"
  • "How does Stripe handle iframe tokenization?"
  • "What does the W3C Payment Request API spec say about browser support?"

Tool Priority

Use tools in this order of preference:

Priority Tool Best For
1 Context7 (resolve-library-id + query-docs) Library/framework documentation — fast, reliable, structured
2 firecrawl (if available) Any URL, broad search, deep research, crawling documentation sites
3 WebFetch Specific URLs the user provides or you discover
4 WebSearch Broad queries — may be blocked by VPCSC in some environments

If a tool is unavailable or returns errors, note it in the report and proceed with alternatives. Never get stuck on one tool.

Process

Phase 1: Plan

Parse the research question. Identify:

  • Source categories to target: official docs, community forums, competitor code, standards bodies, blog posts
  • 3-5 targeted search queries to execute

State the plan briefly before executing.

Phase 2: Search

Execute across multiple source types:

  1. Start with Context7 for any library/framework documentation needs
    • Call resolve-library-id first to get the library ID
    • Then query-docs with a specific question
  2. Use firecrawl or WebSearch for broader queries (blog posts, GitHub issues, Stack Overflow)
  3. Use WebFetch for specific URLs discovered during search or provided by the user
  4. If WebSearch is blocked, note it and rely on Context7 + firecrawl + direct URL fetches

Search discipline:

  • Pursue at least 2-3 different source types for cross-referencing
  • Record the URL of every source as you find it — you will need these for citations
  • Stop when you have sufficient evidence from multiple sources, or when searches stop yielding new information
  • If you can't find information on a sub-topic after 2-3 attempts, record it as a gap

Read the full file on GitHub · 157 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. 12d ago First seen · 157 lines · 55 tokens per session scan A c994a6fe9ccc

Subscribe to this mod's changes

web-research is a skill published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 1,414 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

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