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/tools-for-agents/cortex/agents-mdgit clone --depth 1 https://github.com/tools-for-agents/cortexWhat 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 | $0.00918 | $0.00918 |
| Opus 5 | $0.00459 | $0.00459 |
| Sonnet 5 | $0.00184 | $0.00184 |
| Haiku 4.5 | $0.00092 | $0.00092 |
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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — cortex
🧠 A local, Obsidian-compatible second brain for agents. A wikilinked markdown vault with a knowledge graph (backlinks, auto-healing links), FTS5 search, self-maintenance, and a live graph web view. CLI + web + MCP. Part of tools-for-agents.
Setup
node --version # 22+ required. Nothing to install.
npm test # = node --test (~12s)
CORTEX_VAULT=./vault node scripts/seed.js # put real notes in a vault
CORTEX_VAULT=./vault node src/cli.js serve --port 7800
npm run mcp # the MCP server, stdio
Zero runtime dependencies, and that is a hard rule. No dependencies in package.json, ever. Node 22+
gives you node:sqlite and a test runner.
| Env | For |
|---|---|
CORTEX_VAULT |
the vault directory — always point this at a temp dir in tests |
PORT |
serve port (default 7800). ⚠️ There is no CORTEX_PORT — it is --port or PORT; anything else is silently ignored and it binds 7800 anyway. |
The rules this repo is built on
1. Only the picture is evidence. Run iris against any UI
change and look at the shot before you say it works. This repo was spotless on a desktop and broken four
ways on a 390px phone — with green CI the whole time. Audit phone,tablet,desktop, both themes.
2. Open the doors. Every state behind a button is a state nothing has ever rendered, and every door
opened in this kit so far had a bug behind it. .results is display:none until you type — the gate named
.results .r in its hover list for months, matched nothing, and reported clean about a state it never
reached. Drive the page with --pre, then look.
3. A list that names more than the view renders lies, and it lies in the direction of "clean". Keep each
gate's hover: list to what that page actually shows; put the rest behind a job that opens their door.
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.
- yesterday First seen · 66 lines · 918 tokens per session scan A a2cfcfbfa004
cortex AGENTS.md is an instructions file published in the GitHub repository tools-for-agents/cortex (0 stars, last pushed 27d ago), licensed MIT. It adds 918 tokens to every session, about $0.0046 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.
Other instructions, from other repositories
scout AGENTS.md
AGENTS.md instructions for tools-for-agents/scout, covering agents.md — scout, setup, the rules this repo is built on, tests and ci.
recall AGENTS.md
AGENTS.md instructions for tools-for-agents/recall, covering agents.md — recall, setup, the rules this repo is built on, tests and ci.
obsidian-wiki AGENTS.md
AGENTS.md instructions for Ar9av/obsidian-wiki, covering obsidian wiki — agent context, readme translation parity, configuration, targeting a specific vault and vault structure.
kglite CLAUDE.md
Instructions for kkollsga/kglite, covering kglite — claude code conventions, build & test, architecture, the boundary principle (wrappers vs core) — summary and in-memory is the core product.
vetix AGENTS.md
Instructions for HuTa0kj/vetix, covering vetix — project map, repository layout, workflow, extension points and configuration.
trustabl CLAUDE.md
Instructions for trustabl/trustabl, covering instructions for claude — trustabl, project naming, detection model: five scopes, scanning pipeline and step 1 — recon (cheap, no ast).