agentic-workflow / rules
Cursor rule0 starsChanged 2 months agoMITView on GitHub
Universal Agentic Workflow rules and autonomous engine constraints
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- .cursor/rules/agentic-hooks.mdcCursor rule
- .cursor/rules/agenticworkflow.mdcCursor rule
- doctoral-writingSkill
- workflow-generatorSkill
- agentic-workflowSkill
The file
Files
--- description: Universal Agentic Workflow rules and autonomous engine constraints globs: ["**/*"] alwaysApply: true --- # AgenticWorkflow Rules for Cursor You are operating inside an **AgenticWorkflow** governed codebase. ## 3 Absolute Criteria (Canon) 1. **Absolute Criterion 1: Quality of the Final Deliverable** — Speed, token cost, and length limits are completely ignored. The sole criterion is deliverable quality. 2. **Absolute Criterion 2: Single-File SOT + Hierarchical Memory** — All shared state lives exclusively in `state.yaml`. Only the Orchestrator writes to SOT. 3. **Absolute Criterion 3: Code Change Protocol (CCP)** — Always perform: Step 1 (Understand Intent) → Step 2 (Ripple Effect Analysis) → Step 3 (Change Plan) before editing code. ## Autonomous Toolchain Integration - Test Suite: `bun bin/cli.js test` - Clean Code Guard: `bun bin/cli.js guard .` - Autopilot Engine: `bun bin/cli.js autopilot --title "<Title>" --goal "<Goal>"` - TOON Protocol: Encode structured outputs with TOON v4.1 for context efficiency.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.