RNR-Enhanced-Cognee: Instructions file for Codex

AGENTS.md

RNR-Enhanced-Cognee AGENTS.md is an instructions file for Codex, OpenCode from vincentspereira/RNR-Enhanced-Cognee. It costs 6,855 tokens per session, scanned A, original, Apache-2.0.

Project instructions for implementing an enhanced Cognee memory system in Codex. They require plain ASCII output, configurable categories, and a standard memory-server interface.

In plain words
What is it for?
Use them when changing the RNR Enhanced Cognee implementation, especially for output formatting, category handling, and memory-server integration.
Why use it?
They give the coding agent project-specific rules so its changes and output match the repository's compatibility and design requirements.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: reads ~/.codex or $CODEX_HOME, but also the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Codex.

This is vincentspereira/RNR-Enhanced-Cognee's own configuration. It tells Codex and OpenCode how to work on RNR-Enhanced-Cognee itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything RNR-Enhanced-Cognee configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vincentspereira/RNR-Enhanced-Cognee. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vincentspereira/RNR-Enhanced-Cognee/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/vincentspereira/RNR-Enhanced-Cognee

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for RNR-Enhanced-Cognee AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vincentspereira/rnr-enhanced-cognee/agents-md/github.svg)](https://agentmods.dev/instructions/vincentspereira/rnr-enhanced-cognee/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/vincentspereira/rnr-enhanced-cognee/agents-md"><img src="https://agentmods.dev/badge/instructions/vincentspereira/rnr-enhanced-cognee/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for RNR-Enhanced-Cognee AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vincentspereira/rnr-enhanced-cognee/agents-md"><img src="https://agentmods.dev/badge/instructions/vincentspereira/rnr-enhanced-cognee/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,855 This file is loaded in full into every session.
When invoked 6,855 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.06855 $0.06855
Opus 5 $0.03427 $0.03427
Sonnet 5 $0.01371 $0.01371
Haiku 4.5 $0.00685 $0.00685

Measured 10d ago against content hash a9b17ecec6a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

RNR-Enhanced-Cognee AGENTS.md scanned grade A with 1 finding 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 10d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:26333/collections
AGENTS.md · 960 lines

How it starts

The opening of the file, as written. The whole thing — 960 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RNR Enhanced Cognee Implementation for Codex

Overview

This document is the Codex-facing counterpart to CLAUDE.md. Both files describe the same RNR Enhanced Cognee memory architecture; this one is tuned for the Codex CLI and uses ASCII-only formatting throughout (no emojis, no checkmarks) so it round-trips cleanly through Windows cp1252 consoles.

If you're Claude, read CLAUDE.md. If you're Codex, this file is yours.


CRITICAL REQUIREMENTS

1. ASCII-Only Output (NO Unicode Encoding)

All output must use ASCII characters ONLY. Do NOT use Unicode symbols.

Prohibited:

  • Checkmarks / crosses (no Unicode tick, cross, or x-mark glyphs)
  • Warning symbols (no Unicode warning sign)
  • Emojis of any kind (no chart/wrench/agent/memory/rocket pictographs)
  • Arrows (no Unicode left/right/up/down arrows -- use ->, <-, ^, v)
  • Special symbols (no Unicode info, sparkle, bullet glyphs)

Use ASCII equivalents:

  • Success -> OK or [OK]
  • Warning -> WARN or [WARNING]
  • Error -> ERR or [ERROR]
  • Info -> INFO or [INFO]
  • Document -> [DOC]
  • Library -> [LIB]
  • Agent -> [AGENT]
  • Memory -> [MEM]

Why: Windows console (cp1252 encoding) cannot display Unicode characters. Using Unicode causes UnicodeEncodeError: 'charmap' codec can't encode character ... which kills any process that tries to print to stdout/stderr.

2. Dynamic Categories (NO Hardcoded Categories)

Do NOT use hardcoded categories like ATS/OMA/SMC in code.

WRONG -- hardcoded enum:

class MemoryCategory(Enum):
    ATS = "ats"
    OMA = "oma"
    SMC = "smc"

if category not in ["ats", "oma", "smc"]:
    raise ValueError(f"Invalid category: {category}")

CORRECT -- dynamic category loading from config:

config = EnhancedConfig()
categories = config.category_prefixes  # Loaded from .enhanced-cognee-config.json

def add_memory(agent_id: str, content: str, memory_category: str):
    # Categories are dynamic - accept any string
    # No validation against hardcoded list
    pass

Read the full file on GitHub · 960 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. 10d ago First seen · 960 lines · 6,855 tokens per session scan A a9b17ecec6a3

Subscribe to this mod's changes

RNR-Enhanced-Cognee AGENTS.md is an instructions file published in the GitHub repository vincentspereira/RNR-Enhanced-Cognee (1 stars, last pushed 26d ago), licensed Apache-2.0. It adds 6,855 tokens to every session, about $0.0343 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens