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-viz/claude-mdgit clone --depth 1 https://github.com/cdeust/cortex-vizWhat 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 | $0.00463 | $0.00463 |
| Opus 5 | $0.00231 | $0.00231 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00046 | $0.00046 |
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.
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 --frozenalone does not installpytestormutmut— they live in thedevoptional-dependency group (pyproject.toml's[project.optional-dependencies] dev), and a bare--frozensync skips every extra. Always runuv sync --frozen --extra devin a fresh worktree/clone before testing.- Symptom, not just the fix: this fails silently, not loudly.
uv run pyteststill runs — it just falls through PATH to a systempytest(e.g./opt/homebrew/bin/pytest, a different Python than.venv's) instead of erroring "pytest not found". The tell isuv run which pytestresolving outside.venv/bin/, or DB-backed test modules (test_memory_read.py,test_no_db_mode.py, ...) failing collection withModuleNotFoundError: No module named 'psycopg'even thoughuv 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.
- Symptom, not just the fix: this fails silently, not loudly.
Etiquette
Conventional commits, staged file-by-file. One PR per concern. Do not merge your own PR without the owner's go-ahead.
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 · 21 lines · 463 tokens per session scan A 55469d33ef80
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.
Other instructions, from other repositories
marimo AGENTS.md
Instructions for marimo-team/marimo, covering marimo development guidelines, your primary responsibility is to the project and its users, quick setup, development commands and python.
streamlit copilot-instructions.md
Copilot instructions for streamlit/streamlit, covering streamlit repo overview, tech stack, folder structure, shell & build policy and make commands.
marimo copilot-instructions.md
Instructions for marimo-team/marimo: For example, if there is a frontend change to make a border thicker, how does this look in run mode, app-view and edit-view? For a backend change, has the user tested different scenarios?
latitude-llm AGENTS.md
AGENTS.md instructions for latitude-dev/latitude-llm, covering agents.md, product scope, repo-wide conventions, how to use this guide and skill glossary.
Tracely-ai CLAUDE.md
Claude Code instructions for Jwuthri/Tracely-ai, covering claude.md, commands, architecture, hard rules and gotchas.
semiotic CLAUDE.md
Claude Code instructions for nteract/semiotic, covering semiotic claude code instructions and claude code notes.