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/cdeust/cortex/claude-mdgit clone --depth 1 https://github.com/cdeust/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 | $0.02469 | $0.02469 |
| Opus 5 | $0.01234 | $0.01234 |
| Sonnet 5 | $0.00494 | $0.00494 |
| Haiku 4.5 | $0.00247 | $0.00247 |
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 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@/.claude/rules/model-behavior.md
@/.claude/rules/coding-standards.md
Cortex — Persistent Memory MCP Server
Persistent memory and cognitive profiling MCP server for Claude Code.
Python 3.10+, FastMCP, Pydantic, numpy. Storage: SQLite by default
(plugin installs, .mcpb/Cowork sandboxed launches) or
PostgreSQL+pgvector as the opt-in upgrade (install-plugin.sh --postgres, CLI/dev mode, team databases) — see PRIVACY.md for the
per-surface truth and mcp_server/infrastructure/backend_marker.py
for how the plugin persists the choice.
Problem Statement
Claude Code sessions generate rich behavioral data (tool usage, session duration, first messages, keyword patterns) but this data is lost between sessions. Cortex mines this history to build a cognitive profile per domain and provides a thermodynamic memory system with heat/decay, predictive coding write gates, causal graphs, and intent-aware retrieval.
Build & Test
- Install (dev):
uv sync --no-default-groups --extra dev— SQLite backend adds--extra sqlite. Resolved fromuv.lock, the same source CI installs from; resolving from thepyproject.tomlranges instead gives you versions CI never had (issue #253). - Environment preflight:
python -m mcp_server.doctor(backend-aware check list, fix message per check) - Tests:
pytest(full suite — current count:assets/badge-tests.svg, or runpytest --collect-only -q) ·pytest tests_py/core/(one layer) ·pytest --cov=mcp_server --cov-report=term-missing- Lint BEFORE every commit:ruff check && ruff format --check— the CI enforces both; passing onlyruff checkis not enough. - Type gate (pyright, zero-diagnostic): resolve its environment from
uv.lock(uv sync --no-default-groups --extra … --group typecheck), never from thepyproject.tomlranges — a range-resolved env reads a different type surface than CI and reports diagnostics CI never sees (issue #253). Exact command: CONTRIBUTING.md § Reproducing the pyright gate locally. - Release gate benchmarks (isolated, ephemeral container — the only source
of truth for pre-tag/floor decisions):
benchmarks/reproduce.sh. Do NOT gate a release against the live production database — same-day same-machine checks against it drift ±0.003 on LoCoMo MRR intra-day (measured 2026-07-14,benchmarks/results/repro/20260714-floors-rebaseline/) and nearly false-failed a floor that passes cleanly underreproduce.sh. - Iteration benchmarks:
python3 benchmarks/{longmemeval,locomo,beam}/run_benchmark.py⚠ Consolidation is OFF by default → scores collapse to ≈0%. This is a harness artifact (every candidate is prefiltered by the read-path heat gate before consolidation ever advances the stage), not a bug — pass--with-consolidationfor representative numbers.
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 · 170 lines · 2,469 tokens per session scan A 72d5a225331a
Cortex CLAUDE.md is an instructions file published in the GitHub repository cdeust/Cortex (71 stars, last pushed 3d ago), licensed MIT. It adds 2,469 tokens to every session, about $0.0123 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
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
Instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.