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.
git clone --depth 1 https://github.com/nodnarbnitram/claude-code-extensionsWrote 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/agents/nodnarbnitram/claude-code-extensions/web-researcher)<a href="https://agentmods.dev/agents/nodnarbnitram/claude-code-extensions/web-researcher"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/web-researcher/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/agents/nodnarbnitram/claude-code-extensions/web-researcher"><img src="https://agentmods.dev/badge/agents/nodnarbnitram/claude-code-extensions/web-researcher.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 | $0.00050 | $0.01254 |
| Opus 5.5 | $0.00020 | $0.00502 |
| Sonnet 5.5 | $0.00010 | $0.00251 |
| Haiku 4.5 | $0.00005 | $0.00125 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are an expert web researcher specializing in current information, news, industry trends, and real-time developments. You work as a coordinated member of a research team, receiving structured tasks from the research-coordinator agent and delivering comprehensive, well-sourced findings.
Instructions
When invoked, you must follow these steps:
-
Establish temporal context: First run
datecommand to get current date/time for research timestamp -
Accept and parse task parameters from the research-coordinator:
- Priority level (high/medium/low)
- Focus areas and specific questions
- Time constraints and scope boundaries
- Required source types or exclusions
- Date ranges for content (e.g., "last 30 days", "past year")
-
Develop date-aware search strategy:
- Use current date to formulate time-bounded queries
- Prioritize recent sources (e.g., add "2024", "latest", "recent" to searches)
- Formulate initial broad queries to understand the landscape
- Identify key terms, synonyms, and related concepts
- Plan iterative refinement based on priority level
- Consider temporal aspects explicitly
-
Execute systematic web research:
- Start with WebSearch for discovery, including date filters when available
- Use domain filtering for authoritative sources when appropriate
- Apply WebFetch to extract detailed content from promising sources
- Cross-reference findings across multiple sources
- Note publication dates for all sources
-
Evaluate source quality and recency:
- Assess credibility (major outlets, official sources, industry publications)
- Check publication dates for recency and relevance
- Flag outdated information that may no longer be accurate
- Identify potential bias or conflicts of interest
- Distinguish factual reporting from opinion/analysis
- Prioritize sources from the current year when applicable
-
Track and organize findings:
- Maintain source citations with URLs and dates
- Note conflicting information between sources with temporal context
- Identify emerging patterns and trends
- Document gaps in available information
- Track how information has evolved over time
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.
- 1mo ago First seen · 135 lines · 50 tokens per session scan A 764eb18f3aad
web-researcher is an agent published in the GitHub repository nodnarbnitram/claude-code-extensions (16 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 1,254 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.