agentmods.dev

cortex AGENTS.md

Developer guidance for Cortex, a native macOS app built with SwiftUI that shows and manages a local collection of AI coding tools, sessions, costs, skills, agents, servers, hooks, memory, repositories, and ports.

In plain words
What is it for?
Use it when adding or changing Cortex features, rebuilding the Xcode project, compiling the macOS app, or working within its architecture and conventions.
Why use it?
It explains how the app is organized and built, helping agents avoid breaking generated project files, platform requirements, or shared application state.

Instructions file for CodexOpenCode

5 22d ago B scan 1,464 tokens original MIT
View the source file envibagus/cortex
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/envibagus/cortex/agents-md
Clone the repo
git clone --depth 1 https://github.com/envibagus/cortex

Made for: Codex, OpenCode.

Per session 1,464 This file is loaded in full into every session.
When invoked 1,464 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01464 $0.01464
Opus 5 $0.00732 $0.00732
Sonnet 5 $0.00293 $0.00293
Haiku 4.5 $0.00146 $0.00146

Measured yesterday against content hash 0e32072d8bca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

cortex AGENTS.md scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

which installs reversible Claude Code hooks in `~/.claude/settings.json`. Do not add
AGENTS.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cortex - agent & contributor guide

Context for AI coding agents (and humans) working in this repo. Read this before making changes. Cortex is a native SwiftUI macOS app: a control center for your local AI stack (Claude Code sessions, costs, skills, agents, MCP servers, hooks, memory, repos, ports).

Build & run

xcodegen generate   # regenerate Cortex.xcodeproj from project.yml (run after ADDING or REMOVING a .swift file)
xcodebuild -project Cortex.xcodeproj -scheme Cortex -configuration Debug -destination 'platform=macOS' build
open ~/Library/Developer/Xcode/DerivedData/Cortex-*/Build/Products/Debug/Cortex.app

Or open Cortex.xcodeproj in Xcode and Run. The .xcodeproj is generated and gitignored; project.yml is the source of truth. Requirements: macOS 15+, Xcode 16+. The UI uses macOS 26 Liquid Glass APIs behind availability checks, so the full build wants the macOS 26 SDK / Xcode 26; older Xcode builds the rest with pre-26 fallbacks. Dependency-light: SwiftUI + Swift Charts + MarkdownUI + SwiftDraw only.

Architecture map

  • Cortex/App - AppModel is the single @Observable source of truth (current route, every store, settings, and the refresh orchestration). ContentView is the NavigationSplitView shell + the cmd-K command palette + toasts. Navigation holds the Route enum and sidebar sections. CortexApp owns window config + menu-bar commands.
  • Cortex/Services (all read REAL data, locally, read-only):
    • SessionStore parses ~/.claude/projects/**/*.jsonl into sessions + day buckets.
    • ConfigScanner discovers skills/agents/commands/rules/MCP/hooks/memory/instructions from ~/.claude and the configured scan roots.
    • RepoService (git + gh), PortService (lsof), CostService (pricing), UsageService (live limits), SummaryService (on-device summaries), HygieneEngine (health/security scores), LibraryStore (favorites/collections).
    • ChatService is the Assistant: drives the claude (or agy) CLI as a transport.
    • Shell runs subprocesses and resolves binaries (see gotchas).
  • Cortex/DesignSystem - Theme, Components (Card, GlassSegmentedControl, CortexGroupBoxStyle, Pill, hoverHighlight, PageScaffold, FlowLayout), Charts, MarkdownText.
  • Cortex/Features - one file per route (ReadoutView, AssistantView, SessionsView, ...).
  • Cortex/Models - shared value types (ClaudeSession, ConfigItem, ChatMessage, ...).

Read the full file on GitHub · 92 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 · 92 lines · 1,464 tokens per session scan B 0e32072d8bca

Subscribe to this mod's changes

cortex AGENTS.md is an instructions file published in the GitHub repository envibagus/cortex (5 stars, last pushed 22d ago), licensed MIT. It adds 1,464 tokens to every session, about $0.0073 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Analytics and metricsMemory and contextPlanningaiclaude-codedashboarddeveloper-toolsmacosswiftui
Related

Other instructions, from other repositories

OnlySwitch AGENTS.md

Instructions for jacklandrin/OnlySwitch, covering onlyswitch agent guidance, workflow, context routing and project-specific working rules.

jacklandrin/OnlySwitch · 1,186 tokens

Applite CLAUDE.md

Instructions for milanvarady/Applite, covering claude.md, project overview, build & run, architecture and data flow.

milanvarady/Applite · 2,572 tokens

Vocello AGENTS.md

Instructions for PowerBeef/Vocello, covering agents.md — vocello (qwenvoice), product and authority, start and resume work, hard invariants and domain routing.

PowerBeef/Vocello · 5,212 tokens

skills-manager CLAUDE.md

Instructions for yibie/skills-manager, covering skills manager - development guide, tui engine: blessed, 核心原则, 参考文档 and 正确的 list 用法.

yibie/skills-manager · 642 tokens

TokenEater CLAUDE.md

Instructions for AThevon/TokenEater: The full contributor and agent guide for this project lives in AGENTS.md: repo layout, architecture and data flow, the hard-won SwiftUI rules, and the build / test / release commands.

AThevon/TokenEater · 78 tokens

swift-tui AGENTS.md

Instructions for SwiftTUI/swift-tui, covering agents.md, build & test commands, architecture (one-page summary), development guidelines and code style.

SwiftTUI/swift-tui · 2,410 tokens