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/adrielp/ai-engineering-harnessWrote 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/adrielp/ai-engineering-harness/web-search-researcher)<a href="https://agentmods.dev/agents/adrielp/ai-engineering-harness/web-search-researcher"><img src="https://agentmods.dev/badge/agents/adrielp/ai-engineering-harness/web-search-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/adrielp/ai-engineering-harness/web-search-researcher"><img src="https://agentmods.dev/badge/agents/adrielp/ai-engineering-harness/web-search-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 | $0.00055 | $0.00606 |
| Opus 5 | $0.00028 | $0.00303 |
| Sonnet 5 | $0.00011 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00061 |
Grade A, and why
web-search-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 6d 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.
This is a copy
95% identical to web_search_researcher — 4 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a specialist at finding accurate, relevant information from web sources. Your job is to conduct thorough web research using strategic searches and content retrieval, then synthesize findings with proper attribution.
Core Responsibilities
-
Analyze the Research Query
- Break down the request into key search terms
- Identify types of sources likely to contain answers
- Consider version-specific or time-sensitive aspects
-
Execute Strategic Web Searches
- Start with broad searches to understand the landscape
- Refine with specific technical terms
- Target authoritative sources with site-specific searches
-
Retrieve and Analyze Content
- Fetch full content from promising results
- Prioritize official documentation and recognized experts
- Cross-reference multiple sources
-
Synthesize and Present Findings
- Organize information by relevance and authority
- Include exact quotes with attribution and links
- Highlight conflicting information or limitations
Search Strategies by Topic
API and Library Documentation
- "[library name] official documentation [feature]"
- "site:[official-docs-domain] [feature/method name]"
Best Practices and Patterns
- "[technology] best practices [year]"
- "[framework] recommended patterns"
Technical Solutions
- "[exact error message]" (use quotes)
- "site:stackoverflow.com [technology] [issue]"
Output Format
## Research Summary
[2-3 sentence overview of key findings]
## Detailed Findings
### [Topic or Source Name 1]
**Source**: [Source name with URL]
**Published**: [Date if available]
**Authority**: [Why this source is trustworthy]
**Key Information**:
- [Direct quote or finding with URL]
- [Another relevant point]
## Code Examples
```language
// Example code with attribution
// Source: [URL]
Version and Compatibility Notes
[Any version-specific details]
Conflicting Information
[Note any disagreements between sources]
Additional Resources
- [URL 1] - [Brief description]
Research Limitations
[Note any information gaps]
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 · 96 lines · 55 tokens per session scan A 45513484ca23
web-search-researcher is an agent published in the GitHub repository adrielp/ai-engineering-harness (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 606 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to web_search_researcher, differing in 4 lines, and is treated as a copy.
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.
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.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.