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/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/periodic-planning)<a href="https://agentmods.dev/rules/lwybzss8924d/deepsearchagents/periodic-planning"><img src="https://agentmods.dev/badge/rules/lwybzss8924d/deepsearchagents/periodic-planning/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/rules/lwybzss8924d/deepsearchagents/periodic-planning"><img src="https://agentmods.dev/badge/rules/lwybzss8924d/deepsearchagents/periodic-planning.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 | $0.00000 | $0.00463 |
| Opus 5 | $0.00000 | $0.00231 |
| Sonnet 5 | $0.00000 | $0.00093 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
periodic-planning 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 10d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSearchAgent Periodic Planning
DeepSearchAgent v0.2.4 introduces periodic planning capability for both agent types, allowing strategic reassessment during complex search tasks.
Concept
Periodic planning helps agents maintain focus and adapt their search strategy as they gather new information. Instead of blindly following an initial plan, agents reassess at regular intervals to:
- Evaluate progress on the current goal
- Identify gaps in the information collected
- Adjust search strategy based on discoveries
- Prioritize remaining sub-tasks
Implementation
ReAct Agent
In agent.py, the ReAct agent implements planning with:
# Set planning interval (default: 7)
planning_interval = planning_interval
The planning process involves:
- Initial planning at the start of a task
- Periodic planning every
planning_intervalsteps - Sending special planning prompts to the LLM to reconsider its approach
CodeAct Agent
In codact_agent.py, the CodeAct agent uses:
# Set planning interval (default: 5)
search_planning_interval = planning_interval
The CodeAct planning involves:
- Detailed strategy assessment in Python code
- State tracking for visited URLs, search queries, etc.
- Python-based plan adjustments
Configuration
Planning intervals can be configured in:
-
agents: react: planning_interval: 7 codact: planning_interval: 5 -
Command line:
# For ReAct agent python -m src.agents.cli --agent-type react --react-planning-interval 10 # For CodeAct agent python -m src.agents.cli --agent-type codact --planning-interval 8
Benefits
- More coherent search strategy over long tasks
- Better adaptation to discovered information
- Reduced "tunnel vision" where agent follows initial assumptions
- Improved handling of complex, multi-part research questions
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.
- 10d ago First seen · 77 lines · 0 tokens per session scan A 63bacd70d965
periodic-planning is a cursor rule published in the GitHub repository lwyBZss8924d/DeepSearchAgents (135 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 463 tokens. 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.
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.