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/configurationgit 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/configuration)<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>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 | $0.00758 | $0.00758 |
| Opus 5 | $0.00379 | $0.00379 |
| Sonnet 5 | $0.00152 | $0.00152 |
| Haiku 4.5 | $0.00076 | $0.00076 |
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.
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
- @config.toml configuration file
- Environment Variables: Override config file settings
- 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
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 · 122 lines · 758 tokens per session scan A 8b9766dcea0a
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.
Other cursor rules, from other repositories
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.
family-instance-domain-actions
Family instance domain action implementation patterns.