From 957841237d4b375acd78f2016df89ed28ed23671 Mon Sep 17 00:00:00 2001 From: Sapan Mozammel Date: Sun, 13 Sep 2026 19:53:41 +0600 Subject: [PATCH 1/2] feat(rules): add Auterix universal multi-agent workflow rule and studio directory --- README.md | 2 ++ ...terix-workflow-cursorrules-prompt-file.mdc | 20 +++++++++++++++++++ 2 files changed, 22 insertions(+) create mode 100644 rules/auterix-workflow-cursorrules-prompt-file.mdc diff --git a/README.md b/README.md index 8204dac5..b7a7ff7e 100644 --- a/README.md +++ b/README.md @@ -242,6 +242,7 @@ By adding selected `.mdc` files to `.cursor/rules/`, you can use these rules dir - [Alpha Skills](https://github.com/PatrickJS/awesome-cursorrules/blob/main/rules/alpha-skills-quant-factor-research.mdc) - Quantitative factor research skills for Cursor. Evaluate factors, run backtests, mine new alpha through natural language. - [Anti-Over-Engineering](https://github.com/PatrickJS/awesome-cursorrules/blob/main/rules/anti-overengineering.mdc) - Keeping changes scoped, simple, and directly tied to the user's request. - [Anti-Sycophancy Code Discipline](https://github.com/PatrickJS/awesome-cursorrules/blob/main/rules/anti-sycophancy-code-discipline-cursorrules-prompt-file.mdc) - 17 directives blocking the most common LLM coding honesty failures: hallucinated APIs, invented signatures, false-confidence validation, manufactured-urgency capitulation, authority-driven softening, and self-referential comments. Drop the `.mdc` in `.cursor/rules/`. +- [Auterix (Universal AI Workflow Standard)](https://github.com/PatrickJS/awesome-cursorrules/blob/main/rules/auterix-workflow-cursorrules-prompt-file.mdc) - Deterministic multi-agent context protocol & verification standard synchronizing Cursor with 20 other AI coding assistants. - [Chrome Extension (JavaScript/TypeScript)](https://github.com/PatrickJS/awesome-cursorrules/blob/main/rules/chrome-extension-dev-js-typescript-cursorrules-pro.mdc) - Chrome extension development with JavaScript and TypeScript integration. - [Code Guidelines](https://github.com/PatrickJS/awesome-cursorrules/blob/main/rules/code-guidelines-cursorrules-prompt-file.mdc) - Code development with guidelines integration. - [Code Pair Interviews](https://github.com/PatrickJS/awesome-cursorrules/blob/main/rules/code-pair-interviews.mdc) - Interview practice and collaborative coding sessions. @@ -320,6 +321,7 @@ By adding selected `.mdc` files to `.cursor/rules/`, you can use these rules dir ## Directories +- [Auterix Studio](https://auterix.vercel.app) - Visual multi-agent context compiler, stack detector, and AI readiness scorecard. - [CursorList](https://cursorlist.com) - [CursorDirectory](https://cursor.directory/) diff --git a/rules/auterix-workflow-cursorrules-prompt-file.mdc b/rules/auterix-workflow-cursorrules-prompt-file.mdc new file mode 100644 index 00000000..2728b3c5 --- /dev/null +++ b/rules/auterix-workflow-cursorrules-prompt-file.mdc @@ -0,0 +1,20 @@ +--- +description: Universal multi-agent workflow and context rules for Cursor, synchronizing architectural invariants, verification gates, and zero-drift standards. +globs: **/* +alwaysApply: false +--- +# Auterix Universal Multi-Agent Workflow Standard + +You are an expert full-stack engineer adhering strictly to the Auterix context specification. +When implementing code, refactoring, or reviewing changes, apply the following deterministic rules unconditionally. + +## Core Invariants +1. **Type Safety & Zero Any**: Never introduce untyped `any` or loose type assertions. Export explicit schemas and typed interfaces. +2. **Deterministic Boundaries**: Adhere strictly to project architecture boundaries in `.ai/project.json` and `.cursorrules`. +3. **Zero Secrets in Code**: Never hardcode API keys, tokens, or credentials in client or server files. Use validated environment variables. +4. **Verification First**: Never mark a task complete without running project test suites and linter verification (`npm test`, `npm run lint`). +5. **Progressive Disclosure**: Break down complex tasks into atomic stages (Plan ➔ Implement ➔ Review ➔ Verify) to maintain context window attention. + +## Cross-Agent State +- Keep architectural decisions recorded in `.ai/memory.md`. +- Before suggesting new external libraries or altering database schemas, verify against `.ai/memory.md` conventions to prevent anti-patterns and regressions. From 527a42a3c37200d41f2205bf5da21827cf6aea6f Mon Sep 17 00:00:00 2001 From: Sapan Mozammel Date: Mon, 14 Sep 2026 18:00:35 +0600 Subject: [PATCH 2/2] docs: scope PR to rule file and README catalog entry --- README.md | 1 - 1 file changed, 1 deletion(-) diff --git a/README.md b/README.md index b7a7ff7e..9b79cdb3 100644 --- a/README.md +++ b/README.md @@ -321,7 +321,6 @@ By adding selected `.mdc` files to `.cursor/rules/`, you can use these rules dir ## Directories -- [Auterix Studio](https://auterix.vercel.app) - Visual multi-agent context compiler, stack detector, and AI readiness scorecard. - [CursorList](https://cursorlist.com) - [CursorDirectory](https://cursor.directory/)