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/aaronb305/claude-cortex/claude-mdgit clone --depth 1 https://github.com/aaronb305/claude-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/aaronb305/claude-cortex/claude-md)<a href="https://agentmods.dev/instructions/aaronb305/claude-cortex/claude-md"><img src="https://agentmods.dev/badge/instructions/aaronb305/claude-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 | $0.08938 | $0.08938 |
| Opus 5 | $0.04469 | $0.04469 |
| Sonnet 5 | $0.01788 | $0.01788 |
| Haiku 4.5 | $0.00894 | $0.00894 |
Grade C, and why
claude-cortex CLAUDE.md scanned grade C with 2 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 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| uv | Package management | `pip install uv` or `curl -LsSf https://astral.sh/uv/install.sh \| sh` | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| uv | Package management | `pip install uv` or `curl -LsSf https://astral.sh/uv/install.sh \| sh` | How it starts
The opening of the file, as written. The whole thing — 1,072 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Cortex
Blockchain-style ledger memory with performance-based reinforcement for Claude Code.
Installation
# Install from local directory
cd ~/projects/claude-cortex
./install.sh
# Or install plugin from local marketplace
claude plugin install claude-cortex@claude-cortex --scope user
This will:
- Install the Python package with
uv - Set up hooks in
~/.claude/hooks/ - Configure Claude Code settings
- Initialize the global ledger at
~/.claude/ledger/
Dependencies
All features are included by default with uv sync:
| Feature | Description | Dependencies |
|---|---|---|
| Ledger storage | Blockchain-style learning storage | pydantic, click |
| Full-text search | FTS5 keyword search | sqlite3 (Python stdlib) |
| Semantic search | Vector similarity search | fastembed, sqlite-vec |
| Cryptographic signing | Ed25519 block signatures | cryptography |
| Content-addressed storage | Deduplication via content hash | (included) |
| Distributed sync | Merkle-based ledger sync | (included) |
| Handoffs | Work-in-progress state capture | (included) |
| Summaries | Transcript summary storage | (included) |
| Confidence decay | Time-based confidence adjustment | (included) |
| Cross-project transfer | Learning suggestions & import | (included) |
| File locking | Race condition prevention | fcntl (Python stdlib) |
| Git/PR ingestion | Extract learnings from commits & PRs | gh CLI (for PRs) |
| Entity graph | Code structure tracking | tree-sitter-language-pack |
| MCP tools | Low-latency Claude Code integration | mcp |
External Requirements
| Requirement | Purpose | Install |
|---|---|---|
| Python 3.10+ | Runtime | System package manager |
| uv | Package management | pip install uv or curl -LsSf https://astral.sh/uv/install.sh | sh |
| gh CLI | GitHub PR ingestion | brew install gh or system package manager |
Verify Installation
# Check all dependencies installed
uv sync
# Verify semantic search
uv run python -c "from claude_cortex.search.semantic import is_available; print(is_available())"
# Verify entity extraction
uv run python -c "from claude_cortex.entities.extractors import get_extractor_for_file; print(get_extractor_for_file('test.py'))"
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 · 1,072 lines · 8,938 tokens per session scan C d976498f1016
claude-cortex CLAUDE.md is an instructions file published in the GitHub repository aaronb305/claude-cortex (2 stars, last pushed 5mo ago), licensed MIT. It adds 8,938 tokens to every session, about $0.0447 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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).
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.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).