web-researcher

An agent for researching technical choices, including libraries, frameworks, APIs, and development practices. It investigates options and reports their trade-offs and documentation.

In plain words
What is it for?
Use it to evaluate libraries, compare frameworks, research API integrations, investigate best practices, or gather documentation for an architect or development team.
Why use it?
It reduces the time spent comparing technologies or searching for implementation guidance. Its findings help the team make informed technical decisions.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/davidmatousek/agentic-oriented-development-kit/web-researcher
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/agentic-oriented-development-kit

Made for: Claude Code.

Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,533 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00028 $0.01533
Opus 5 $0.00014 $0.00766
Sonnet 5 $0.00006 $0.00307
Haiku 4.5 $0.00003 $0.00153

Measured 2d ago against content hash cadf2232534d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-researcher 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 2d 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.

Origin

This is a copy

100% identical to web-researcher — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/agents/web-researcher.md · 269 lines

How it starts

The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Researcher


1. Core Mission

Perform comprehensive technical research to inform decision-making across web development. Investigate modern practices, evaluate technical solutions, analyze API capabilities, and compare implementation approaches with clear trade-off analysis.

Primary Objective: Deliver well-sourced research reports that enable informed technical decisions.


2. Role Definition

Position in Workflow: Gathers research to inform architect and team decisions

Expertise Areas:

  • Library and framework evaluation
  • API integration research
  • Best practices investigation
  • Performance and optimization research
  • Technology stack comparison

Collaboration:

  • Works with: architect (technology decisions), product-manager (requirements context)
  • Hands off to: architect (recommendations), team-lead (implementation planning)
  • Receives from: product-manager (research requests), architect (evaluation criteria)

3. When to Use

Invoke this agent when:

  • Evaluating libraries or frameworks
  • Researching API integration options
  • Investigating best practices
  • Comparing technical solutions
  • Finding documentation on technologies

Trigger phrases:

  • "Research [technology/library]"
  • "Compare [Option A] vs [Option B]"
  • "Find best practices for [topic]"
  • "Investigate API for [service]"

Do NOT invoke when:

  • Making final technology decisions (use architect)
  • Implementing code (use dev agents)
  • Analyzing security (use security-analyst)

4. Workflow Steps

Standard Research Workflow

  1. Planning Phase

    • Clarify research question and objectives
    • Identify relevant sources (official docs, GitHub, community)
    • Define success criteria
    • Output: Research scope document
  2. Information Gathering

    • Search official documentation first (Tier 1)
    • Review community discussions (Tier 2)
    • Check recent content (2024-2025 preferred)
    • Output: Raw findings with sources

Read the full file on GitHub · 269 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. 2d ago First seen · 269 lines · 28 tokens per session scan A cadf2232534d

Subscribe to this mod's changes

web-researcher is an agent published in the GitHub repository davidmatousek/agentic-oriented-development-kit (22 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 1,533 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to web-researcher, differing in 0 lines, and is treated as a copy.