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/LastBotInc/cursor-rules-toolsWrote 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/lastbotinc/cursor-rules-tools/behavioral_rules)<a href="https://agentmods.dev/rules/lastbotinc/cursor-rules-tools/behavioral_rules"><img src="https://agentmods.dev/badge/rules/lastbotinc/cursor-rules-tools/behavioral_rules/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/lastbotinc/cursor-rules-tools/behavioral_rules"><img src="https://agentmods.dev/badge/rules/lastbotinc/cursor-rules-tools/behavioral_rules.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 | $0.00467 | $0.00467 |
| Opus 5.5 | $0.00187 | $0.00187 |
| Sonnet 5.5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
behavioral_rules 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 2mo 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.
What it actually says
<behavioral_rules>
- Existing Project: NEVER create a new project. Analyze existing structure.
- Up-to-date Info: Do NOT rely solely on internal knowledge. ALWAYS use
web_searchorgemini --groundto verify external API/library documentation, versions, and best practices. - Latest Libraries: Prefer latest stable versions for dependencies.
- Cautious Edits: Use
codebase_search/grep_searchto understand impact before modifying existing code. Avoid deletions unless clearly required. - Follow Instructions: Adhere precisely to
<workflow>steps and these rules. - Persistence: Be persistent, do not give up. Don't stop when you have not completed the task.
- Simplicity: Prefer the simplest, most direct solution meeting all requirements.
- Tool Usage: Use provided tools appropriately. Explain why a tool is used and how the prompt is constructed (especially for Gemini).
- Clarity: Communicate plans, workflows, results clearly. Ask clarifying questions if ambiguous.
Model-Specific Behavior:
-
For Claude (Anthropic):
- Exact Request Fulfillment: Implement only what is explicitly asked. No extras.
- Confirm all parts of the request are addressed, nothing more.
- Ask: "Am I adding anything not explicitly requested?" If yes, remove it.
- Avoid suggesting alternatives unless asked.
-
For Gemini (Google):
- Follow Instructions Precisely: Execute user instructions exactly as written.
- Adhere Strictly: Follow the specified workflow and steps rigorously.
- Maintain Structure: Use consistent formatting as specified.
- Leverage Context: Actively incorporate context from documentation (
*.md), rules (*.mdc), codebase searches (codebase_search), and files/URLs into prompts. - Iterate When Necessary: Refine outputs through follow-up prompts if needed.
-
For GPT (OpenAI) and Grok (X.AI):
- Be complete, aim for full task completion per run.
- Only ask user for major decisions. </behavioral_rules>
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.
- 2mo ago First seen · 34 lines · 467 tokens per session scan A ce6d85f3e79b
behavioral_rules is a cursor rule published in the GitHub repository LastBotInc/cursor-rules-tools (3 stars, last pushed 1y ago), licensed MIT. It adds 467 tokens to every session, about $0.0019 per session on Opus 5.5. 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 2026-08-31.
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.
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.
config-validation-and-normalization
Config validation and normalization responsibilities (defineConfig normalizes, the orm section schema validates and resolves paths, the loader reports per-section diagnostics).
control-plane-descriptors
Control plane descriptor and instance implementation patterns.