configuration

configuration is a cursor rule for Cursor from lwyBZss8924d/DeepSearchAgents. It costs 758 tokens per session, scanned A, original, MIT.

A set of rules for configuring DeepSearchAgent, an AI system that searches and analyzes information. Settings can come from a TOML file, environment variables, or command-line arguments, with later sources taking priority.

In plain words
What is it for?
Use it to choose models, set reasoning or execution step limits, control streaming and verbosity, and override settings for a particular run.
Why use it?
It keeps model choices, agent behavior, execution limits, and output detail in one configurable place instead of hard-coding them.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

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 rules/lwybzss8924d/deepsearchagents/configuration
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 configuration

README.md
[![agentmods](https://agentmods.dev/badge/rules/lwybzss8924d/deepsearchagents/configuration.svg)](https://agentmods.dev/rules/lwybzss8924d/deepsearchagents/configuration)
Your own site
<a href="https://agentmods.dev/rules/lwybzss8924d/deepsearchagents/configuration"><img src="https://agentmods.dev/badge/rules/lwybzss8924d/deepsearchagents/configuration.svg" alt="Measured on agentmods" height="20"></a>
Per session 758 This file is loaded in full into every session.
When invoked 758 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00758 $0.00758
Opus 5 $0.00379 $0.00379
Sonnet 5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 6d ago against content hash 8b9766dcea0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

configuration 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.

.cursor/rules/configuration.mdc · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepSearchAgent Configuration

DeepSearchAgent uses a flexible configuration system with multiple options for customization.

Configuration Sources

  1. @config.toml configuration file
  2. Environment Variables: Override config file settings
  3. Command Line Arguments: Highest precedence overrides

Key Configuration Sections

Model Configuration

models:
  orchestrator_id: "openrouter/openai/o4-mini-high"  # Main LLM orchestration
  search_id: "openrouter/openai/o4-mini-high"        # Search model (if different)
  reranker_type: "jina-reranker-m0"                  # Reranker model type

Common Agent Settings

agents:
  common:
    verbose_tool_callbacks: true  # Show full tool inputs/outputs

ReAct Agent Settings

agents:
  react:
    max_steps: 25                # Max reasoning steps
    enable_streaming: false      # Enable streaming output (recommended: false)
    planning_interval: 7         # Interval for planning steps

CodeAct Agent Settings

agents:
  codact:
    executor_type: "local"       # Code execution environment
    max_steps: 25                # Max execution steps
    verbosity_level: 1           # 0=minimal, 1=normal, 2=verbose
    enable_streaming: false      # Enable streaming response (recommended: false)
    planning_interval: 4         # Interval for planning steps
    # Additional options
    executor_kwargs: {}          # Additional executor parameters
    additional_authorized_imports: []  # Additional allowed Python imports

Service Configuration

service:
  host: "0.0.0.0"
  port: 8000
  version: "0.2.4.dev"
  deepsearch_agent_mode: "codact"  # Default agent type

Logging Configuration

logging:
  litellm_level: "WARNING"        # Reduce INFO logs from LiteLLM
  filter_repeated_logs: true      # Enable repeated log filtering
  filter_cost_calculator: true    # Filter cost calculation logs
  filter_token_counter: true      # Filter token count logs
  format: "minimal"               # Use simplified format

Read the full file on GitHub · 122 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. 6d ago First seen · 122 lines · 758 tokens per session scan A 8b9766dcea0a

Subscribe to this mod's changes

configuration is a cursor rule published in the GitHub repository lwyBZss8924d/DeepSearchAgents (135 stars, last pushed 1y ago), licensed MIT. It adds 758 tokens to every session, about $0.0038 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.