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/tecnomanu/pampaWrote 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/tecnomanu/pampa/pampa-project-structure)<a href="https://agentmods.dev/rules/tecnomanu/pampa/pampa-project-structure"><img src="https://agentmods.dev/badge/rules/tecnomanu/pampa/pampa-project-structure.svg" alt="Measured on agentmods" 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 | $0.00570 |
| Opus 5 | $0.00000 | $0.00285 |
| Sonnet 5 | $0.00000 | $0.00114 |
| Haiku 4.5 | $0.00000 | $0.00057 |
Grade A, and why
pampa-project-structure 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 8d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PAMPA Project Structure Guide
This is the PAMPA (Protocol for Augmented Memory of Project Artifacts) project - an MCP-compatible semantic code search system.
Core Architecture Files
Main Entry Points
- cli.js - Command line interface, handles
npx pampacommands - mcp-server.js - MCP server that exposes tools to AI agents
- package.json - Project configuration and dependencies
Core Engine
- service.js - Core business logic: indexing, searching, chunking
- indexer.js - Tree-sitter based code parsing and chunking
- providers.js - Embedding providers (OpenAI, Transformers, Ollama, Cohere)
Generated Files
- pampa.codemap.json - Lightweight index committed to git
.pampa/pampa.db- SQLite database with vectors and metadata (not committed).pampa/chunks/*.gz- Compressed code chunks (not committed)
Technology Stack
- Node.js - Runtime environment
- SQLite3 - Local vector database
- Tree-sitter - Code parsing and AST analysis
- OpenAI/Transformers.js - Embedding generation
- MCP Protocol - AI agent communication
- gzip - Code chunk compression
Key Concepts
- Chunking: Code is split into semantic units (functions, classes, methods)
- Embedding: Each chunk gets vectorized for semantic search
- Indexing: Vectors + metadata stored in local SQLite
- Codemap: Git-friendly JSON index for context portability
- MCP Serving: Tools exposed to AI agents via MCP protocol
Development Workflow
- CLI Development: Modify cli.js for new commands
- MCP Tools: Add tools in mcp-server.js
- Core Logic: Business logic goes in service.js
- New Providers: Add embedding providers in providers.js
File Patterns
*.js- Main application code*.md- Documentation and rules.pampa/- Generated database and chunks (gitignored)examples/- Test projects for validationtest/- Test suite
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.
- 8d ago First seen · 58 lines · 0 tokens per session scan A 4c109a740f24
pampa-project-structure is a cursor rule published in the GitHub repository tecnomanu/pampa (30 stars, last pushed 11mo ago), licensed ISC. It costs nothing until one of its globs matches a file; then it loads 570 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
cardano-mcp
These rules complement our main development collaboration rules, focusing specifically on the Model Context Protocol (MCP) server project with TypeScript. This project serves as a specialized RAG (Retrieval-Augmented Generation) gateway to existing Cardano resources, documentation, and tools to assist with dApp…
005_Dynamo_KV_Cache_Management_KVBM
NVIDIA Dynamo KV Cache Management (KVBM) - Advanced memory management and offloading strategies for optimal performance.
elizaos_v2_core_memory
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐ │ Memory Creation │ │ State Composition│ │ Knowledge Base │ │ & Storage │───▶│ & Context Build │───▶│ Integration │ │ │ │ │ │ │ │ - Memory Types │ │ - Provider Data │ │ - Document Proc │ │ - Validation │ │ - Context Merge │ │ - Embeddings │.
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.