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.
npx agentmods add instructions/turfptax/cortex-core/claude-mdgit clone --depth 1 https://github.com/turfptax/cortex-coreWrote 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.
[](https://agentmods.dev/instructions/turfptax/cortex-core/claude-md)<a href="https://agentmods.dev/instructions/turfptax/cortex-core/claude-md"><img src="https://agentmods.dev/badge/instructions/turfptax/cortex-core/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02992 | $0.02992 |
| Opus 5 | $0.01496 | $0.01496 |
| Sonnet 5 | $0.00598 | $0.00598 |
| Haiku 4.5 | $0.00299 | $0.00299 |
Grade B, and why
cortex-core CLAUDE.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 3d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
ssh [email protected] "sudo mv /tmp/*.py /home/turfptax/cortex-core/src/ && sudo chown root:root /home/turfptax/cortex-core/src/*.py && sudo systemctl restart cortex-core" How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cortex Core — AI Agent Guide
THIS FILE IS COMMITTED AND PUBLIC. Never put real personal data, client or employer names, secrets, or private-life details in this file or any tracked file. All instance-specific values live in gitignored config (see
SECURITY.mdand the gitignoredmemory/core/*.md). When you need real context, read those gitignored files; do not bake their contents into tracked code or docs.
If you're an AI agent starting work in this repo, read this first.
ACTIVE DIRECTION (2026-07-14): cloud migration. Cortex is moving off the home Pi into Azure (one Container App per person; this core becomes the cloud engine, co-deployed with the gateway, single writer of the SQLite files). Read
docs/CLOUD_MIGRATION.mdbefore any core/deploy work. Near-term core tasks are P0 (env-externalize) and P1 (gateway reads the core SQLite), both local, no Azure needed.
What this repo is
Cortex Core is the Pi-side of Cortex, Tory Moghadam's personal AI memory system. The Python runtime lives in src/. The interpretive memory layer (overseer plugin) lives in plugins/overseer/.
Cortex serves three functions:
- F1 — Serve digital data to future AIs for context (primary mission; the reason the system exists)
- F2 — Tory's personal data-org software (Hub UI is on the cortex-desktop side, but the storage + interpretive layer lives here)
- F3 — R&D testbed for AI maturation (sibling dispatch, B/C agents, dialectic, voice mode)
The mission was articulated by Tory in his own words 2026-05-26: "to save and process all my digital data for future serving to new AIs for context."
Boot sequence for new AIs (read in this order)
1. The agentic triangle — three identity files
memory/core/ holds three identity files defining the agents in the room:
| File | What |
|---|---|
memory/core/USER.md |
Who Tory is. Gitignored — exists locally on this machine. If you can read it, do. If not, read example.USER.md for the structure + ask Tory for the actual file content. |
memory/core/OVERSEER.md |
The memory-upkeep agent's identity. Gitignored. Same fallback. |
memory/core/APP.md |
Cortex's self-description. Gitignored. Same fallback. |
memory/core/example.*.md |
Public templates with placeholders — always tracked. |
memory/core/README.md |
Explains the gitignore pattern. |
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.
- 3d ago First seen · 228 lines · 2,992 tokens per session scan B a3c4240390ba
cortex-core CLAUDE.md is an instructions file published in the GitHub repository turfptax/cortex-core (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,992 tokens to every session, about $0.0150 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
agents-remember AGENTS.md
Instructions for Foxfire1st/agents-remember, covering agents remember source checkout instructions, start here — route by role, memory and onboarding, memory retrieval strategies and source layout.
Perenna AGENTS.md
Instructions for scarletkc/Perenna, covering perenna agent guidelines, start with the project contract, environment, implementation boundaries and generated and versioned artifacts.
nobrainr CLAUDE.md
Claude Code instructions for vicquick/nobrainr, covering nobrainr — collective agent memory service, what this is, canonical categories, architecture and routing (when using a reverse proxy).
mcp-memory-server CLAUDE.md
Instructions for foxj77/mcp-memory-server, covering claude.md, what this repo is, chart layout, build / run / test and local build + run.
mem0-mcp-selfhosted CLAUDE.md
Instructions for elvismdev/mem0-mcp-selfhosted, covering claude.md, mcp servers, build & test commands and architecture.
Muninn GEMINI.md
Gemini CLI instructions for wjohns989/Muninn, covering muninn mcp — sota+ development context, 🚀 sota+ development philosophy, 🛠 operational guidelines (always-on), 🏗 system architecture and 📂 project structure.