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.
npx agentmods add rules/lwybzss8924d/deepsearchagents/toolsgit clone --depth 1 https://github.com/lwyBZss8924d/DeepSearchAgentsWrote 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/rules/lwybzss8924d/deepsearchagents/tools)<a href="https://agentmods.dev/rules/lwybzss8924d/deepsearchagents/tools"><img src="https://agentmods.dev/badge/rules/lwybzss8924d/deepsearchagents/tools.svg" alt="Measured on agentmods" 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 | $0.01166 | $0.01166 |
| Opus 5 | $0.00583 | $0.00583 |
| Sonnet 5 | $0.00233 | $0.00233 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
tools 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 4d 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSearchAgent Tools System
DeepSearchAgent features a comprehensive toolchain for web search, content processing, and analysis. These tools are designed to work with both the CodeAct and ReAct agent paradigms.
Tool Interface System
- tools/init.py: Exports all tools with consistent naming:
- All tools inherit from
smolagents.Toolbase class - Provides uniform interface across both agent paradigms
- Standardizes imports for agent initialization
- All tools inherit from
Search and Web Content Tools
Search Tool
-
search.py: Performs web search via Serper API
- Core class:
SearchLinksToolwith standardized interface - Returns JSON-formatted search results with titles, links, and snippets
- Configurable search location and result count
- Integrates with CLI for rich progress display
- Core class:
-
serper.py: Core search engine implementation
SerperAPIclass handles direct API communication- Uses typed
SearchResult[T]container for error handling - Implements comprehensive field extraction and result processing
- Clean separation between tool interface and API implementation
URL Reader Tool
- readurl.py: Extracts content from web pages
ReadURLToolclass interfaces with Jina Reader API- Supports different output formats (markdown, text)
- Implements asynchronous content scraping with robust error handling
- Uses context management for proper resource cleanup
Text Processing Tools
Text Chunking System
-
chunk.py: Tool interface for intelligent text segmentation
ChunkTextToolclass provides simple interface for agents- Delegates chunking requests to the specialized segmenter implementation
- Optimized for error handling and clean result formatting
- Returns JSON-formatted string of chunked text segments
-
segmenter.py: Advanced text segmentation
JinaAISegmenterclass offers high-quality text chunking- Implements both synchronous and asynchronous interfaces
- Features robust retry mechanisms and error handling
Chunkerwrapper class maintains backward compatibility- Advanced asynchronous batch processing for multiple texts
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.
- 4d ago First seen · 132 lines · 1,166 tokens per session scan A faadd046239f
tools is a cursor rule published in the GitHub repository lwyBZss8924d/DeepSearchAgents (135 stars, last pushed 1y ago), licensed MIT. It adds 1,166 tokens to every session, about $0.0058 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 2026-08-30.
Other cursor rules, from other repositories
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.