project-overview

project-overview is a cursor rule for Cursor from lwyBZss8924d/DeepSearchAgents. It costs 1,200 tokens per session, scanned A, original, MIT.

A project guide describing DeepSearchAgent, a system for web search and reasoning that can also run code. ReAct means combining reasoning with actions, while CodeAct means using executable code as part of the agent’s work.

In plain words
What is it for?
Use it when working on DeepSearchAgent files such as agents, prompts, configuration, streaming models, text chunking, embeddings, and tools.
Why use it?
It gives a coding agent background on the project’s structure, components, and intended ways of working.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it when working on DeepSearchAgent files such as agents, prompts, configuration, streaming models, text chunking, embeddings, and tools.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/lwybzss8924d/deepsearchagents/project-overview
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.

Clone the repo
git clone --depth 1 https://github.com/lwyBZss8924d/DeepSearchAgents

Made for: Cursor.

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 project-overview

README.md
[![agentmods](https://agentmods.dev/badge/rules/lwybzss8924d/deepsearchagents/project-overview.svg)](https://agentmods.dev/rules/lwybzss8924d/deepsearchagents/project-overview)
Your own site
<a href="https://agentmods.dev/rules/lwybzss8924d/deepsearchagents/project-overview"><img src="https://agentmods.dev/badge/rules/lwybzss8924d/deepsearchagents/project-overview.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,200 This file is loaded in full into every session.
When invoked 1,200 The same file — it is already loaded in full.
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 $0.01200 $0.01200
Opus 5 $0.00600 $0.00600
Sonnet 5 $0.00240 $0.00240
Haiku 4.5 $0.00120 $0.00120

Measured 8d ago against content hash 54d691bce927, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

project-overview 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 8d 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.

.cursor/rules/project-overview.mdc · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepSearchAgent Project

DeepSearchAgent is an intelligent agent system that combines the ReAct (Reasoning + Acting) framework and the CodeAct concept (executable code agents) to enable deep web search and reasoning capabilities.

Project Structure

src/agents/
├── agent.py                # ReAct agent implementation
├── cli.py                  # Command-line interface
├── codact_agent.py         # CodeAct agent implementation
├── config_loader.py        # Configuration loading utilities
├── main.py                 # FastAPI web service
├── prompt_templates/       # Modular prompt template system
│   ├── codact_prompts.py   # CodeAct agent prompts
│   └── react_prompts.py    # ReAct agent prompts
├── streaming_agents.py     # Streaming agent implementations
├── streaming_models.py     # Streaming model wrappers
├── core/                   # Core implementation classes
│   └── chunk/              # Text chunking components
│       └── segmenter.py    # Jina AI Segmenter implementation
└── tools/                  # Tool implementations
    ├── chunk.py            # Text chunking tool
    ├── embed.py            # Text embedding tool
    ├── final_answer.py     # Final answer generation tool
    ├── readurl.py          # URL content reading tool
    ├── rerank.py           # Content reranking tool
    ├── search.py           # Web search tool
    └── wolfram.py          # Wolfram Alpha computational tool

Version

Current version: 0.2.4.dev (as specified in pyproject.toml)

Core Components

Agent Implementations

Read the full file on GitHub · 116 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. 8d ago First seen · 116 lines · 1,200 tokens per session scan A 54d691bce927

Subscribe to this mod's changes

project-overview is a cursor rule published in the GitHub repository lwyBZss8924d/DeepSearchAgents (135 stars, last pushed 1y ago), licensed MIT. It adds 1,200 tokens to every session, about $0.0060 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.