cortex-viz CLAUDE.md

cortex-viz CLAUDE.md is an instructions file for coding agents from cdeust/cortex-viz. It costs 463 tokens per session, scanned A, original, MIT.

Project-specific instructions for a read-only visualization service called cortex-viz, which exposes stored information for viewing rather than editing.

In plain words
What is it for?
Use them when developing or testing the Python and JavaScript visualization service, including its server, handlers, and supporting layers.
Why use it?
They document the repository's boundaries, testing setup, and operational details so changes can be made and checked without accidentally writing to stored data.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/cdeust/cortex-viz/claude-md
Clone the repo
git clone --depth 1 https://github.com/cdeust/cortex-viz
Per session 463 This file is loaded in full into every session.
When invoked 463 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00463 $0.00463
Opus 5 $0.00231 $0.00231
Sonnet 5 $0.00093 $0.00093
Haiku 4.5 $0.00046 $0.00046

Measured 3d ago against content hash 55469d33ef80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cortex-viz 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 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.

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.

CLAUDE.md · 21 lines

What it actually says

cortex-viz

Standalone read-only visualization MCP for Cortex (published as hypermnesia-mcp-viz). Python + JavaScript.

Global rules are imported, not restated:

@/.claude/rules/model-behavior.md @/.claude/rules/coding-standards.md

Repo-specific constraints

  • Read-only over Cortex's store: this server never writes memories.
  • The plugin install is live-mounted onto this clone; respawn the standalone HTTP server after editing Python or the running process keeps the old code.
  • Layers: core / server / infrastructure / handlers / hooks / shared / errors.
  • uv sync --frozen alone does not install pytest or mutmut — they live in the dev optional-dependency group (pyproject.toml's [project.optional-dependencies] dev), and a bare --frozen sync skips every extra. Always run uv sync --frozen --extra dev in a fresh worktree/clone before testing.
    • Symptom, not just the fix: this fails silently, not loudly. uv run pytest still runs — it just falls through PATH to a system pytest (e.g. /opt/homebrew/bin/pytest, a different Python than .venv's) instead of erroring "pytest not found". The tell is uv run which pytest resolving outside .venv/bin/, or DB-backed test modules (test_memory_read.py, test_no_db_mode.py, ...) failing collection with ModuleNotFoundError: No module named 'psycopg' even though uv run python -c "import psycopg" succeeds — the module-level import works fine standalone; only the wrong pytest interpreter can't see it. A scoped run against a couple of test files can look completely green while the full suite silently loses its collection of every DB-touching module — the whole point of --frozen (a reproducible, verifiable environment) is defeated by exactly the case it's meant to prevent.

Etiquette

Conventional commits, staged file-by-file. One PR per concern. Do not merge your own PR without the owner's go-ahead.

Changes

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.

  1. 3d ago First seen · 21 lines · 463 tokens per session scan A 55469d33ef80

Subscribe to this mod's changes

cortex-viz CLAUDE.md is an instructions file published in the GitHub repository cdeust/cortex-viz (4 stars, last pushed 10d ago), licensed MIT. It adds 463 tokens to every session, about $0.0023 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.