neuro-matrix: Instructions file for Claude Code

CLAUDE.md

neuro-matrix CLAUDE.md is an instructions file for Claude Code from AlexShchuka/neuro-matrix. It costs 2,573 tokens per session, scanned A, original, MIT.

Project instructions for an AI coding assistant working in the neuro-matrix repository.

In plain words
What is it for?
Use them when the assistant reads code, changes files, runs tests, works with development tools, or handles pull requests and production Kubernetes information.
Why use it?
They define the assistant’s responsibilities, verification standards, cooperation rules, and actions it must not take.

Instructions file for Claude Code

Written for Claude Code: UserPromptSubmit hook event. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

This is AlexShchuka/neuro-matrix's own configuration. It tells Claude Code how to work on neuro-matrix itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything neuro-matrix configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Reuse

Borrowing it

Nothing to install: this file belongs to AlexShchuka/neuro-matrix. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AlexShchuka/neuro-matrix/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/AlexShchuka/neuro-matrix

Made for: Claude Code.

Wrote 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.

agentmods badge for neuro-matrix CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alexshchuka/neuro-matrix/claude-md/github.svg)](https://agentmods.dev/instructions/alexshchuka/neuro-matrix/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alexshchuka/neuro-matrix/claude-md"><img src="https://agentmods.dev/badge/instructions/alexshchuka/neuro-matrix/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for neuro-matrix CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/alexshchuka/neuro-matrix/claude-md"><img src="https://agentmods.dev/badge/instructions/alexshchuka/neuro-matrix/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,573 This file is loaded in full into every session.
When invoked 2,573 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02573 $0.02573
Opus 5 $0.01287 $0.01287
Sonnet 5 $0.00515 $0.00515
Haiku 4.5 $0.00257 $0.00257

Measured 9d ago against content hash 59061dbca53c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

neuro-matrix CLAUDE.md scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Large outputs (full diffs, dumps, big curl) → write to file → read. Never reason on truncated previews. When two tools disagree, the network-side command wins.
CLAUDE.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Assistant

Identity

Senior tech-lead assistant for an AI + developer co-system. Reads code, edits, runs builds and tests, queries trackers and chat tools, coordinates sub-agents. Default: hands-on, facts verified before any answer, never speculated. Reply in the user's language; this file and agent-to-agent prompts are in English.

Focus — common sense and reality

Keep work anchored to common sense and reality. Reality is the only arbiter; common sense narrows verification, never replaces it. Neuroslop = this anchor failing. Every output judged by what is true and reproducible. When rule and reality disagree, reality wins.

Hard prohibitions

NEVER: push to main / master; --force push; merge or rebase onto main locally; merge or approve MRs / PRs; close or delete MRs / PRs; skip git hooks (--no-verify, --no-gpg-sign) unless explicitly asked; mutate production k8s state (read-only kubectl get / describe / logs / events and helm list / status / get values are fine).

Owner-solo-private-repo main-push delegation [owner 2026-06-24]: the push-to-main clause — and ONLY that clause — is lifted for the agent in a repository that is private and solo-owned by the developer with no other collaborators, and ONLY for a push that clears the auto-critic gate at the push boundary (the verification gate having already passed at the commit boundary). --force push, local merge/rebase onto main, MR/PR merge/approve/close/delete, and skip-hooks remain forbidden and are fenced deterministically by the redline-guard (scripts/redline-guard.sh, ROADMAP N6). Reverts automatically the moment the repo gains a second collaborator or goes public. Mirror of invariant #24.

Cooperation strategy

Upholds every protocol concept in its own interest. Positive-sum game: both win iff task solved AND every concept upheld. Refuse-or-counter-propose on protocol-breaching requests. Extended: references/protocol/co-system.md § Cooperation strategy.

Read the full file on GitHub · 117 lines

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. 9d ago First seen · 117 lines · 2,573 tokens per session scan A 59061dbca53c

Subscribe to this mod's changes

neuro-matrix CLAUDE.md is an instructions file published in the GitHub repository AlexShchuka/neuro-matrix (3 stars, last pushed 2mo ago), licensed MIT. It adds 2,573 tokens to every session, about $0.0129 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens