| Dimension | Shared | Only in A | Only in B | Overlap |
|---|---|---|---|---|
| Sections | 0 | 0 | 9 | 0% |
| Commands | 0 | 0 | 0 | — |
| Section tags | 0 | 0 | 4 | 0% |
What each file covers
Sections
0 shared · 0 only in A · 9 only in B- + ⚡ Essential Commands
- + 🧠 Understanding Vrooli's True Nature
- + Core Vision
- + The Intelligence Loop
- + 📋 Task Management
- + 🔧 AI Maintenance Tracking
- + ❌ Critical Rules
- + 📁 Documentation Structure
- + 🎯 Remember The Mission
Commands
neither file has anySection tags
0 shared · 0 only in A · 4 only in B- + code-style
- + architecture
- + do-not
- + docs
Line diff
Vrooli/Vrooli · .cursor/rules/agent.mdc
@@ −1 @@
1---
2description:
3globs:
4alwaysApply: true
5---
6You are working on *Vrooli*, an innovative web application that orchestrates AI agents for complex tasks. Follow these guidelines to ensure cohesive execution and continuous process improvement.
7
81. Project Orientation
9- **Documentation Check:**
10 - [README.md](mdc:README.md) Understand the project vision, roadmap, and overall requirements.
11 - [README.md](mdc:docs/architecture/README.md) and [TASKS.md](mdc:TASKS.md): Review project structure and task planning guidelines.
12- **Planning & Learning:**
13 - Draft a brief plan before coding and await confirmation.
14 - After plan confirmation, store the active plan in a markdown file in the `/scratch` folder for future reference.
15 - As you work on the task, you are encouraged to store other things in the `/scratch` folder like things you'd attempted and how they worked out, discoveries on how certain parts of the code work, etc.
16- **Development Standards:**
17 - Use ESM TypeScript for all code.
18 - Include comprehensive docstrings and clear comments on complex logic.
19 - Write unit tests using Mocha, Chai, and Sinon.
20 - Use relative imports with the `.js` extension, but remember when searching for files to use the typed counterpart (`.ts` or `.tsx`).
21- **Dependencies:**
22 - **Never** install new packages without explicit permission!
23
242. Dynamic Task Management with Documentation Update
25- **A. Task Identification and Clarification**
26 - Analyze each new task description to classify it (debugging, UI component creation, refactoring, etc.) and ask clarifying questions if needed.
27- **B. Documentation Consultation & Integration**
28 - Search the `/docs` directory for an appropriate process guide based on the task type.
29 - If no guide exists, confirm whether to use default practices and consider creating one.
30- **C. Execution & Updates**
31 - Use file operations (read/write, search, grep) to retrieve and update process guides.
32 - If deviations from current guidelines occur, ask:
33 "I've noted differences from our documented process. Update `/docs/<relevant-guide>.md`?"
34
353. Feedback and Continuous Improvement
36- **Monitor Communication:**
37 - Detect signs of frustration or terse commands. When detected, prompt:
38 "It seems we might need to refine our process—shall we adjust the guidelines?"
39- **Session Retrospective:**
40 - After completing a task, ask:
41 "Do you have any suggestions or improvements for our process?"
42 - Record actionable feedback to update [agent.mdc](mdc:.cursor/rules/agent.mdc) (this prompt) and/or documentation promptly.
43
444. Autonomous Task Commands
45- **Task Command Reference:**
46 - All task commands and their detailed descriptions are defined in [TASKS.md](mdc:TASKS.md).
47 - Follow the command patterns defined in that file when executing any task operation
48 - Any updates to command behavior should be made directly in [TASKS.md](mdc:TASKS.md) as the single source of truth
49 - Commands in this context are not scripts to be executed - they are processes to follow
50
51
52
Vrooli/Vrooli · .cursor/rules/memory.mdc
@@ +1 @@
1---
2description: Vrooli Intelligence System - Core Instructions
3globs:
4alwaysApply: true
5---
6You are working on Vrooli - a **self-improving intelligence system** where agents build tools that make future agents smarter in an infinite recursive loop. This is NOT just an automation platform.
7
8## ⚡ Essential Commands
9- `vrooli help` - See all available commands
10- `vrooli test help` - See test commands
11- `vrooli develop` - Start development environment
12- `./scripts/manage.sh setup --yes yes` - Initial setup
13
14## 🧠 Understanding Vrooli's True Nature
15
16### Core Vision
17- **Recursive Intelligence**: Every app built becomes a permanent capability
18- **Compound Learning**: System literally cannot forget solutions, only improves
19- **Shared Resources**: Apps share N8n, Redis, Qdrant, PostgreSQL to collaborate
20- **Scenarios = Businesses**: Not tests! Each scenario generates $10K-50K value
21
22### The Intelligence Loop
231. Agent solves problem → Solution crystallized as app/workflow
242. Future agents use solution as building block → More complex problems solvable
253. Each iteration makes ALL future iterations more powerful → ∞
26
27## 📋 Task Management
28Use keywords to trigger commands:
29- **"organize next task"** - Process first unstructured task
30- **"start next task"** - Begin highest priority task
31- **"update task statuses"** - Review and update progress
32- **"research"** - Deep dive on topics
33- **"suggest new tasks"** - Analyze for improvements
34
35## 🔧 AI Maintenance Tracking
36- Before work: `rg "AI_CHECK:.*TASK_ID" --type ts`
37- After work: `// AI_CHECK: TASK_ID=count | LAST: YYYY-MM-DD`
38- Details: `/docs/ai-maintenance/README.md`
39
40## ❌ Critical Rules
411. **NEVER** create files unless absolutely necessary
422. **ALWAYS** prefer editing existing files
433. **NEVER** install packages without permission
444. **NEVER** create documentation unless explicitly requested
455. **ALWAYS** read `/docs/context.md` and CLAUDE.md at session start
46
47## 📁 Documentation Structure
48Core files to read at session start:
49- `/CLAUDE.md` - Primary instructions (this overrides defaults!)
50- `/docs/context.md` - Project overview
51- `/docs/scratch/` - Previous session notes
52
53## 🎯 Remember The Mission
54Every line of code becomes **permanent intelligence** the system uses forever. You're not building features - you're expanding the system's ability to understand and solve problems autonomously.
55
56**When in doubt:** Read `/CLAUDE.md` - it contains the most up-to-date instructions and overrides everything else.
@@ −1 +1 @@
11 ---
2−description:
2+description: Vrooli Intelligence System - Core Instructions
33 globs:
44 alwaysApply: true
55 ---
6−You are working on *Vrooli*, an innovative web application that orchestrates AI agents for complex tasks. Follow these guidelines to ensure cohesive execution and continuous process improvement.
6+You are working on Vrooli - a **self-improving intelligence system** where agents build tools that make future agents smarter in an infinite recursive loop. This is NOT just an automation platform.
77
8−1. Project Orientation
9−- **Documentation Check:**
10− - [README.md](mdc:README.md) Understand the project vision, roadmap, and overall requirements.
11− - [README.md](mdc:docs/architecture/README.md) and [TASKS.md](mdc:TASKS.md): Review project structure and task planning guidelines.
12−- **Planning & Learning:**
13− - Draft a brief plan before coding and await confirmation.
14− - After plan confirmation, store the active plan in a markdown file in the `/scratch` folder for future reference.
15− - As you work on the task, you are encouraged to store other things in the `/scratch` folder like things you'd attempted and how they worked out, discoveries on how certain parts of the code work, etc.
16−- **Development Standards:**
17− - Use ESM TypeScript for all code.
18− - Include comprehensive docstrings and clear comments on complex logic.
19− - Write unit tests using Mocha, Chai, and Sinon.
20− - Use relative imports with the `.js` extension, but remember when searching for files to use the typed counterpart (`.ts` or `.tsx`).
21−- **Dependencies:**
22− - **Never** install new packages without explicit permission!
23−
24−2. Dynamic Task Management with Documentation Update
25−- **A. Task Identification and Clarification**
26− - Analyze each new task description to classify it (debugging, UI component creation, refactoring, etc.) and ask clarifying questions if needed.
27−- **B. Documentation Consultation & Integration**
28− - Search the `/docs` directory for an appropriate process guide based on the task type.
29− - If no guide exists, confirm whether to use default practices and consider creating one.
30−- **C. Execution & Updates**
31− - Use file operations (read/write, search, grep) to retrieve and update process guides.
32− - If deviations from current guidelines occur, ask:
33− "I've noted differences from our documented process. Update `/docs/<relevant-guide>.md`?"
8+## ⚡ Essential Commands
9+- `vrooli help` - See all available commands
10+- `vrooli test help` - See test commands
11+- `vrooli develop` - Start development environment
12+- `./scripts/manage.sh setup --yes yes` - Initial setup
3413
35−3. Feedback and Continuous Improvement
36−- **Monitor Communication:**
37− - Detect signs of frustration or terse commands. When detected, prompt:
38− "It seems we might need to refine our process—shall we adjust the guidelines?"
39−- **Session Retrospective:**
40− - After completing a task, ask:
41− "Do you have any suggestions or improvements for our process?"
42− - Record actionable feedback to update [agent.mdc](mdc:.cursor/rules/agent.mdc) (this prompt) and/or documentation promptly.
14+## 🧠 Understanding Vrooli's True Nature
4315
44−4. Autonomous Task Commands
45−- **Task Command Reference:**
46− - All task commands and their detailed descriptions are defined in [TASKS.md](mdc:TASKS.md).
47− - Follow the command patterns defined in that file when executing any task operation
48− - Any updates to command behavior should be made directly in [TASKS.md](mdc:TASKS.md) as the single source of truth
49− - Commands in this context are not scripts to be executed - they are processes to follow
16+### Core Vision
17+- **Recursive Intelligence**: Every app built becomes a permanent capability
18+- **Compound Learning**: System literally cannot forget solutions, only improves
19+- **Shared Resources**: Apps share N8n, Redis, Qdrant, PostgreSQL to collaborate
20+- **Scenarios = Businesses**: Not tests! Each scenario generates $10K-50K value
5021
22+### The Intelligence Loop
23+1. Agent solves problem → Solution crystallized as app/workflow
24+2. Future agents use solution as building block → More complex problems solvable
25+3. Each iteration makes ALL future iterations more powerful → ∞
5126
27+## 📋 Task Management
28+Use keywords to trigger commands:
29+- **"organize next task"** - Process first unstructured task
30+- **"start next task"** - Begin highest priority task
31+- **"update task statuses"** - Review and update progress
32+- **"research"** - Deep dive on topics
33+- **"suggest new tasks"** - Analyze for improvements
5234
35+## 🔧 AI Maintenance Tracking
36+- Before work: `rg "AI_CHECK:.*TASK_ID" --type ts`
37+- After work: `// AI_CHECK: TASK_ID=count | LAST: YYYY-MM-DD`
38+- Details: `/docs/ai-maintenance/README.md`
39+
40+## ❌ Critical Rules
41+1. **NEVER** create files unless absolutely necessary
42+2. **ALWAYS** prefer editing existing files
43+3. **NEVER** install packages without permission
44+4. **NEVER** create documentation unless explicitly requested
45+5. **ALWAYS** read `/docs/context.md` and CLAUDE.md at session start
46+
47+## 📁 Documentation Structure
48+Core files to read at session start:
49+- `/CLAUDE.md` - Primary instructions (this overrides defaults!)
50+- `/docs/context.md` - Project overview
51+- `/docs/scratch/` - Previous session notes
52+
53+## 🎯 Remember The Mission
54+Every line of code becomes **permanent intelligence** the system uses forever. You're not building features - you're expanding the system's ability to understand and solve problems autonomously.
55+
56+**When in doubt:** Read `/CLAUDE.md` - it contains the most up-to-date instructions and overrides everything else.
