project-directives

A shared set of hand-written development rules for every AI agent working in a repository. The rules live in source files and can be synchronized into the copies agents use.

In plain words
What is it for?
It helps define coding standards, system requirements, installation instructions, and commands for the memory-fabric package. It also documents how to update and synchronize those rules.
Why use it?
It keeps agents following the same project requirements and prevents edits to generated copies from being lost or causing inconsistencies.

Cursor rule for Cursor

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/elvirafa/agentic-memory/project-directives
Clone the repo
git clone --depth 1 https://github.com/elViRafa/agentic-memory

Made for: Cursor.

Per session 1,116 This file is loaded in full into every session.
When invoked 1,116 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.

ModelPer sessionOnce invoked
Fable 5 $0.01116 $0.01116
Opus 5 $0.00558 $0.00558
Sonnet 5 $0.00223 $0.00223
Haiku 4.5 $0.00112 $0.00112

Measured yesterday against content hash 32f9e5be692e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-directives 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.

.cursor/rules/project-directives.mdc · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Directives — Memory Fabric

Hand-curated development guidelines shared by every AI agent working on this repo. Source of truth: the role: steering section files in .ai-memory/. Edit those files (review via MR), then run ai-memory sync-agents — never edit this generated copy in place.

Framework Rules Map

This section provides the high-level system requirements and CLI usage overview for the memory-fabric package.

1. System Requirements

  • Python Version: Python >= 3.11
  • Core Dependencies:
    • mcp >= 1.0.0 (optional; required only if running as an MCP server).
    • ripgrep (rg): optional but highly recommended to speed up searches.

2. Installation Conventions

# CLI only
pip install "git+https://github.com/elViRafa/agentic-memory.git"

# CLI + MCP Server
pip install "memory-fabric[mcp] @ git+https://github.com/elViRafa/agentic-memory.git"

3. Command Line Interface (CLI)

The package installs a global executable ai-memory:

ai-memory [--cwd <path>] [--json] <command>

Supported Commands Overview:

  • init, status, doctor, eval, dream, query, sync-global, rollback.

(For detailed schemas returned by these CLI commands, see the CLI Contracts Map)

4. Testing Conventions

  • Use standard pytest for all unit and integration testing. Run pytest tests/ from the root directory.

Granular Rules

Specific rule sets and agent instructions are stored in the granular memory store:

MCP Agent Instructions

Strict rules on how AI Agents should interact with the .ai-memory/ directory using MCP tools rather than standard OS filesystem tools. 👉 View Agent Instructions

Ubiquitous Language

A shared glossary of domain terms utilized in the development, testing, and operation of Memory Fabric.

Core Concepts

Memory Fabric

The local-first, file-first memory layer system. It provides a standardized way for AI assistants to read, write, evaluate, and maintain context across coding sessions.

Read the full file on GitHub · 128 lines

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.

  1. yesterday First seen · 128 lines · 1,116 tokens per session scan A 32f9e5be692e

Subscribe to this mod's changes

project-directives is a cursor rule published in the GitHub repository elViRafa/agentic-memory (2 stars, last pushed 14d ago), licensed MIT. It adds 1,116 tokens to every session, about $0.0056 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.