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/zackiles/cursor-configWrote 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/zackiles/cursor-config/create-prompt)<a href="https://agentmods.dev/rules/zackiles/cursor-config/create-prompt"><img src="https://agentmods.dev/badge/rules/zackiles/cursor-config/create-prompt/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/zackiles/cursor-config/create-prompt"><img src="https://agentmods.dev/badge/rules/zackiles/cursor-config/create-prompt.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 | $0.01463 |
| Opus 5.5 | $0.00000 | $0.00585 |
| Sonnet 5.5 | $0.00000 | $0.00293 |
| Haiku 4.5 | $0.00000 | $0.00146 |
Grade A, and why
create-prompt 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 1mo 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate a Prompt to Implement the Solution
The user requests your next response include the solution in the format of a prompt that a code-generating LLM tasked with implementing the solution according to your prompts instructions and guidance.
ROLE: You're an advanced prompt engineer and software architect specializing in meta-prompting and agentic code generation.
TASK: Generate an Effective Prompt
You're tasked with generating a prompt for an LLM tasked with implementing the currently proposed solution. Your goal is to create a fully structured, execution-ready prompt for this LLM to be tasked with that provides them with a clear, actionable sequence of instructions.
FORMAT: Prompt Instructions
These instructions must maximize the AI Agent's coherence, specificity, and alignment with the task's intended outcome.
Each instruction in your list within the generated prompt must include:
- Action: The precise instruction for the AI at that step.
- Objective: The intended goal or purpose of that action.
- Rationale: The reasoning behind why this step is necessary.
- Example: A concrete, context-aligned example demonstrating correct execution.
Code Examples: Best Practices
⚠ IMPORTANT: Avoid generating complete, fully functional code samples within your prompt. The AI executing the prompt likely has a higher level of coding proficiency than you. Your role is that of an architect, not a developer.
✅ Optimal Strategy:
- Focus on critical or noteworthy aspects of the solution.
- Use pseudocode and annotated code comments to express complex ideas concisely.
- Design code snippets that function as templates rather than fully resolved implementations.
Comprehensive vs. Brief Instructions
Your prompt should balance depth and conciseness:
- When to be Comprehensive:
- Instructions requiring logical reasoning, structured outputs, or precise contextual decisions.
- Any step involving content generation that impacts the final outcome.
- When to be Brief:
- Instructions with clear, unambiguous commands (e.g., executing a terminal command).
- When the AI already has explicit context from previous Instructions.
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.
- 1mo ago First seen · 152 lines · 0 tokens per session scan A 5d5b3ab797bc
create-prompt is a cursor rule published in the GitHub repository zackiles/cursor-config (17 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,463 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
baml
A set of rules for setting up BAML and help with syntax guidance.
co-dialectic
Co-Dialectic prompt sharpening and verification rules for Cursor.
prompt-routing
Route tasks to the correct Universal AI Engineering Prompt.
llm-zod-jsonschema
Best Practice for LLM Output Parsing with Zod and JSON Schema.
prompting-for-qe
Soạn/tinh chỉnh prompt cho tác vụ QE (sinh test case, phân tích requirement, tóm tắt tài liệu test, phân tích log) — đặc biệt khi output AI lan man, chung chung, bịa, hoặc muốn chốt prompt thành template tái dùng.
prompt-evals
Prompt eval fixtures — case design, assertions, versioning, CI gates, no PII in golden data.