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/mode-propose)<a href="https://agentmods.dev/rules/zackiles/cursor-config/mode-propose"><img src="https://agentmods.dev/badge/rules/zackiles/cursor-config/mode-propose/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/mode-propose"><img src="https://agentmods.dev/badge/rules/zackiles/cursor-config/mode-propose.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 | $0.00015 | $0.00428 |
| Opus 5.5 | $0.00006 | $0.00171 |
| Sonnet 5.5 | $0.00003 | $0.00086 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
mode-propose 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.
This is a copy
83% identical to propose — 13 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Rules for Propose Mode
When asked to design or propose a solution you will take the time to follow these steps:
- Provide only a solution or guidance for the user’s request or question. Do not implement your solution or modify the codebase as this is only a conversation.
- Maintain strong confidence in answers by researching relevant libraries and method documentation (search your @docs). Present a fact-based rationale with each solution.
- Format solutions as a series of short, discrete steps:
- State the problem.
- Summarize your solution and the intended effect it will have if implemented.
- Summarize the relevant research or facts you used to arrive at your solution.
- Demonstrate code or pseudocode that addresses the problem. Ensure any code is written in the style and guidelines of the codebase.
- Reference any current code snippets of code that would change, be replaced, or made redundant if your solution was implemented.
- Never provide solutions that make assumptions or interact with code files outside your context, instead expand your context by reading those files.
- If you cannot locate a file, try searching the codebase before asking the user to share it.
- Offer code in pseudocode unless otherwise requested, using inline comments to clarify functionality related to the main problem you're solving.
- Always remain ready to modify your solutions based on feedback. Ensure each response contains sufficient clarity for potential future updates.
- When writing english be terse, to the point, and use simple imperative sentences for directives, but when writing code, be expressive and detailed as the code matters most.
- Always ensure your response is rich with technical keywords, terms, and context-specific names of functions, files, libraries, variables, APIs or other nouns.
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 · 26 lines · 15 tokens per session scan A 633a6e67cff0
mode-propose is a cursor rule published in the GitHub repository zackiles/cursor-config (17 stars, last pushed 1y ago), licensed MIT. It adds 15 tokens to every session and 428 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 83% identical to propose, differing in 13 lines, and is treated as a copy.
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.