What is cortex-mcp AGENTS.md?

A set of instructions that tells a coding agent how to use Cortex, a project-tracking service, during each work session.

Use it to start and end coding sessions, retrieve the next task, track changed files and progress, update features and tests, and check project reminders.

It keeps the agent aligned with the project's current state and assigned work instead of letting it choose tasks on its own. It also records progress, tests, warnings, and session summaries.

cortex-mcp AGENTS.md — Instructions file by neuralnexustech

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/neuralnexustech/cortex-mcp/agents-md

Clone the repo

git clone --depth 1 https://github.com/neuralnexustech/cortex-mcp

Made for: Codex, OpenCode.

Per session 1,573 This file is loaded in full into every session.

When invoked 1,573 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	$0.01573	$0.01573
Opus 5	$0.00787	$0.00787
Sonnet 5	$0.00315	$0.00315
Haiku 4.5	$0.00157	$0.00157

Measured 2d ago against content hash cb3cd2d22bb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cortex-mcp 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 · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cortex MCP — Agent Guide

This file tells AI coding agents how to use Cortex effectively. Read this at session start.

Quick Start

First call: cortex_get_state — get compressed project context (<200 tokens)
Get next task: cortex_get_next_task — NEVER decide your own next step
Work on the task — write code, create files
Track progress:
- cortex_tick_file — when you create/finish a file
- cortex_log_progress — after every significant step
- cortex_update_feature — when a feature milestone is reached
- cortex_add_test / cortex_update_test — when you write/run tests
Check health: cortex_check_reminders — handle ALL warnings before continuing
End session: cortex_save_snapshot — compress session to summary

Session Lifecycle

START → cortex_get_state → cortex_get_next_task → WORK → cortex_check_reminders → ... → cortex_save_snapshot → END

Every Session Start

cortex_get_state → knows project, stack, goals, open issues, last progress

Every Task

cortex_get_next_task → get highest-priority pending todo
  ↓
Work (write code, create files)
  ↓
cortex_tick_file → track each file created
  ↓
cortex_log_progress → log what you did
  ↓
cortex_check_reminders → handle warnings
  ↓
cortex_get_next_task → get next todo (or "ALL TASKS COMPLETE")

Every Session End

cortex_save_snapshot → compress everything to summary

Tool Reference (31 tools)

Core Loop (5 tools)

Tool	When	Purpose
`cortex_get_state`	Session start	Compressed project context
`cortex_get_next_task`	Before each task	Highest-priority pending todo
`cortex_log_progress`	After each step	Log completed work
`cortex_check_reminders`	After each task	6 safety checks
`cortex_save_snapshot`	Session end	Compress session summary

Project Setup (3 tools)

Tool	Purpose
`cortex_init`	Initialize project (ask 10 questions first!)
`cortex_set_active_project`	Switch between projects
`cortex_health`	DB integrity + auto-repair

Read the full file on GitHub · 172 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.

2d ago First seen · 172 lines · 1,573 tokens per session scan A cb3cd2d22bb3

Subscribe to this mod's changes

cortex-mcp AGENTS.md is an instructions file published in the GitHub repository neuralnexustech/cortex-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 1,573 tokens to every session, about $0.0079 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.

Project management

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

cortex-mcp AGENTS.md