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/mikesquared-agency/cortex/claude-mdgit clone --depth 1 https://github.com/MikeSquared-Agency/cortexWrote 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/mikesquared-agency/cortex/claude-md)<a href="https://agentmods.dev/instructions/mikesquared-agency/cortex/claude-md"><img src="https://agentmods.dev/badge/instructions/mikesquared-agency/cortex/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 | $0.01549 | $0.01549 |
| Opus 5 | $0.00775 | $0.00775 |
| Sonnet 5 | $0.00310 | $0.00310 |
| Haiku 4.5 | $0.00155 | $0.00155 |
Grade A, and why
cortex CLAUDE.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Cortex Agent Guide
What is this?
Cortex is an embedded graph memory engine for AI agents. Rust, redb (embedded DB), gRPC + HTTP APIs, vector search (HNSW), auto-linking.
Repo structure
crates/
cortex-core/ — Storage, graph, vector, auto-linker, types. The library.
cortex-server/ — gRPC/HTTP server, CLI, config. The binary.
cortex-client/ — Rust gRPC client crate.
cortex-proto/ — Protobuf definitions + generated code.
warren-adapter/ — Optional Warren integration (feature-gated).
sdks/
typescript/ — cortex-memory-client npm package
python/ — cortex-memory-client PyPI package (`cortex_memory` import)
go/ — Go client module
specs/ — Design specs (tagged IMPLEMENTED/DEFERRED)
docs/ — User-facing documentation
examples/ — Integration examples (LangChain, CrewAI, etc.)
Build & test
cargo test --workspace # All 176 tests
cargo test --workspace --no-default-features # Without warren adapter
cargo build -p cortex-server --release # Release binary
cargo clippy --workspace # Lint
Run
cortex init # Create cortex.toml
cortex serve # Start server (gRPC :9090, HTTP :9091)
cortex node create --kind fact --title "..."
cortex search "query"
cortex briefing <agent-id>
cortex shell # Interactive REPL
Key types
NodeKind/Relation— validated string newtypes (not enums)Cortex::open(path)— library mode, no server neededStoragetrait —RedbStorageimplements itIngestAdaptertrait — pluggable event sourcesTrustEngine-- computes trust from graph topology, no stored confidenceBriefingRoleConfig-- maps node kinds to briefing roles (identity, persistent, trackable, temporal, reviewable, superseding)BriefingScope-- Agent (default), Shared (cross-agent), Unified (orchestrator)- Entity convention:
kind: "entity"+metadata.entity_type - Config:
cortex.tomlwith#[serde(default)]on all structs
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.
- 4d ago First seen · 147 lines · 1,549 tokens per session scan A 996cd71a76a4
cortex CLAUDE.md is an instructions file published in the GitHub repository MikeSquared-Agency/cortex (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,549 tokens to every session, about $0.0077 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 2026-08-30.
Other instructions, from other repositories
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.