Cortex AGENTS.md

A repository-wide instruction file for coding agents working on the Cortex project. It tells them to use Cortex MCP, a connected tool server, for file changes, commands, planning, memory, and quality checks.

In plain words
What is it for?
It guides agent sessions, planning, memory updates, documentation checks, quality gates, and approved file or artifact changes.
Why use it?
It gives agents one shared set of project rules and a defined way to work. This reduces inconsistent behavior and helps preserve project notes and checks.

Instructions file for CodexOpenCode

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 instructions/igrechuhin/cortex/agents-md
Clone the repo
git clone --depth 1 https://github.com/igrechuhin/Cortex

Made for: Codex, OpenCode.

Per session 5,621 This file is loaded in full into every session.
When invoked 5,621 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 $0.05621 $0.05621
Opus 5 $0.02811 $0.02811
Sonnet 5 $0.01124 $0.01124
Haiku 4.5 $0.00562 $0.00562

Measured 2d ago against content hash 8af657462440, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Cortex AGENTS.md 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 2d 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.

AGENTS.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS

Workspace-wide rules for all IDE/AI agents in this repository.

Use Cortex MCP (MANDATORY)

This project has a Cortex MCP server that provides tools for everything agents need. Always use Cortex MCP tools instead of reading files or running commands directly.

Tools (14 — write/execute operations)

Tool Purpose
manage_file() Memory bank read/write (zero-arg reads activeContext.md)
plan() Plan create/list/get/complete/register/archive_completed
update_memory_bank() Roadmap/progress/activeContext mutations
session() Session start, orientation, compact
run_quality_gate() Phase A quality checks and Step 12 final gate (zero-arg)
autofix() Auto-fix lint/format/types/markdown (zero-arg)
think() Reasoning scratchpad
ingest() Stage raw external sources under memory-bank for /cortex/ingest
run_docs_gate() Phase B docs validation (zero-arg)
pipeline_handoff() Inter-phase state exchange (init/write/read/clear)
write_artifact() Allowlisted skill JSON and Synapse rule artifact writes
compress_memory_bank() Compress project CLAUDE.md and memory-bank markdown to reduce session tokens
memory_wal() Memory-bank WAL read, anomaly hints, snapshot/restore
propose_framework_optimization() Draft/self-test a Synapse prompt/rule change in an isolated, always-removed worktree

Resources (6 — read-only, all static/zero-arg)

URI Purpose
cortex://health/connection Health check
cortex://structure Path/structure discovery
cortex://context Context loading (task from session config)
cortex://rules Coding standards (task from session config)
cortex://validation Timestamps/roadmap sync validation
cortex://analysis End-of-session analysis (target from session config)

Quick reference

Need Use Do NOT
Project context cortex://context resource or manage_file() Read .cortex/memory-bank/ files directly
Coding rules, standards cortex://rules resource Read .cortex/rules/ or .cortex/synapse/ directly
Type annotations Read rules via cortex://rules before coding; Pydantic models for internal data; object only for MCP tool params Use Any type; skip loading rules
Markdown formatting docs/guides/markdown-formatting.md Use bold for section titles (use #/##/### instead)
Quality fixes autofix() Run language-specific formatters/linters manually
Tests and pre-commit run_quality_gate() Run pytest/ruff/black/pyright directly
Quality pipeline reference docs/api/tools.md — zero-arg quality tools Legacy parameterized pre-commit tools or job polling when the bridge strips args
Memory bank, roadmap, plans manage_file(), plan(), update_memory_bank() Edit .cortex/ files directly
Project structure, paths cortex://structure resource Hardcode .cortex/ paths

Read the full file on GitHub · 241 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. 2d ago First seen · 241 lines · 5,621 tokens per session scan A 8af657462440

Subscribe to this mod's changes

Cortex AGENTS.md is an instructions file published in the GitHub repository igrechuhin/Cortex (3 stars, last pushed 2d ago), licensed MIT. It adds 5,621 tokens to every session, about $0.0281 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.

Related

Other instructions, from other repositories

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

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

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 · 5,182 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 · 4,345 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

next.js 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