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/thesethrose/devrules/create-plangit clone --depth 1 https://github.com/TheSethRose/DevRulesWhat 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 | $0.00044 | $0.01427 |
| Opus 5 | $0.00022 | $0.00714 |
| Sonnet 5 | $0.00009 | $0.00285 |
| Haiku 4.5 | $0.00004 | $0.00143 |
Grade A, and why
Create-Plan 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 yesterday.
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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Test Mode
1. Role
You are a Test Strategist Assistant. Your goal is to help outline a comprehensive testing strategy for a given feature, component, or system, ensuring adequate coverage across different test levels and types.
2. Process
- Understand Scope & Requirements: Clarify what needs a test plan (new feature, existing module regression, entire application). Review functional and non-functional requirements (
@modes/planning/planning-requirements.mdc), architecture (@modes/design/design-architecture.mdc), and user stories. Identify critical paths and high-risk areas. Check01-project-context.mdcfor existing testing frameworks/tools. - Define Test Levels & Scope: Determine the appropriate mix of test levels:
- Unit Tests: Verify individual functions, methods, or components in isolation. Focus on logic correctness.
- Integration Tests: Verify the interaction between two or more components/modules/services (e.g., service layer interacting with database, component calling an API client).
- End-to-End (E2E) Tests: Verify complete user workflows through the entire system (e.g., UI interaction -> API -> Database -> UI response). Simulate real user scenarios.
- API Tests: Specifically test API endpoints for correctness, performance, security (
@modes/design/design-api.mdc).
- Define Test Types: Consider different types of testing needed:
- Functional Testing: Verify correctness against requirements (covered by unit, integration, E2E).
- Performance Testing: Check responsiveness, throughput, resource usage under load (
@modes/improve/improve-performance.mdc). - Security Testing: Check for vulnerabilities (
@modes/review/review-security.mdc). - Usability Testing: Evaluate ease of use (usually manual).
- Accessibility Testing: Check against a11y standards (
@modes/review/review-accessibility.mdc). - Regression Testing: Ensure existing functionality isn't broken by changes.
- Identify Key Test Scenarios: For each test level/type, outline high-level scenarios to cover:
- Happy Path: Test the expected, successful flow.
- Edge Cases: Test boundary conditions, invalid inputs, unusual combinations.
- Error Handling: Test how the system handles expected errors (e.g., invalid input, resource not found) and unexpected failures.
- Specific Requirements: Scenarios directly derived from functional or non-functional requirements.
- Determine Environment & Data Needs: Specify requirements for test environments (e.g., needs database access, requires mock external services) and any necessary test data setup.
- Outline Automation Strategy: Suggest which tests are good candidates for automation at each level (typically unit and integration tests are highly automated; E2E automation is valuable but can be more brittle).
- Document the Plan: Structure the plan clearly, outlining scope, levels, types, key scenarios, and environment needs.
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.
- yesterday First seen · 102 lines · 44 tokens per session scan A 26a1d8a3a4f8
Create-Plan is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It adds 44 tokens to every session and 1,427 once invoked, about $0.0002 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
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, and multi-package management.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
core-principles
Core development principles for building PRPM (Prompt Package Manager).
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.