Project rules for Tenets, an MCP server, command-line tool, and Python library that finds, ranks, and combines relevant code from a codebase for AI assistants. They cover architecture, Python style, testing, and development commands.

Use them when editing Tenets' code, MCP server, command-line interface, data models, storage, tests, or development configuration.

They help an agent make changes that fit the project's structure and existing development practices.

cursorrules — Cursor rule by jddunn

Install

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.

agentmods

npx agentmods add rules/jddunn/tenets/cursorrules

Clone the repo

git clone --depth 1 https://github.com/jddunn/tenets

Made for: Cursor.

Per session 511 This file is loaded in full into every session.

When invoked 511 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00511	$0.00511
Opus 5	$0.00255	$0.00255
Sonnet 5	$0.00102	$0.00102
Haiku 4.5	$0.00051	$0.00051

Measured yesterday against content hash 03e2e9c51741, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cursorrules 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 yesterday.

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.

.cursorrules · 81 lines

What it actually says

Tenets Project Rules

Project Overview

Tenets is an MCP server, CLI, and Python library for intelligent code context. It helps AI coding assistants understand codebases by finding, ranking, and aggregating relevant code.

Architecture

Core Components

tenets/core/ - Core logic (NLP, ranking, analysis)
tenets/mcp/ - MCP server implementation
tenets/cli/ - CLI application (Typer)
tenets/models/ - Pydantic data models
tenets/storage/ - SQLite session storage

Key Classes

Tenets in tenets/__init__.py - Main API class
TenetsMCP in tenets/mcp/server.py - MCP server
ContextResult in tenets/models/context.py - Distill output

Code Style

Python

Use type hints for all function parameters and returns
Docstrings in Google style
Pydantic for data models
Lazy imports for heavy dependencies (ML, viz)

Testing

pytest for all tests
Tests in tests/ mirroring tenets/ structure
Use fixtures from conftest.py

Commits

Conventional commits: feat, fix, docs, test, chore
1-2 line messages, human-readable

Development Commands

# Install for development
pip install -e ".[dev,mcp]"

# Run tests
pytest

# Run linting
ruff check tenets/

# Type checking
mypy tenets/

# Build docs
mkdocs serve

MCP Server

Running

tenets-mcp              # stdio transport
tenets-mcp --sse        # SSE transport
tenets-mcp --http       # HTTP transport

Testing Tools

Use the MCP inspector or call tools directly via Python:

from tenets import Tenets
t = Tenets()
result = t.distill("find auth code")

Important Notes

No hardcoded paths - Use pathlib and relative paths
Local-first - No external API calls for core features
Lazy loading - Heavy imports (ML, viz) are lazy loaded
Version sync - Keep pyproject.toml and init.py in sync

Changes

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.

yesterday First seen · 81 lines · 511 tokens per session scan A 03e2e9c51741

Subscribe to this mod's changes

cursorrules is a cursor rule published in the GitHub repository jddunn/tenets (8 stars, last pushed 2mo ago), licensed MIT. It adds 511 tokens to every session, about $0.0026 per session on Opus 5. 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 2026-08-31.

Data and AI Planning Testing mcp mcp-server prompt-engineering-tool

cursorrules