What is neat CLAUDE.md?

Repository instructions for NEAT, a system that builds a live, searchable map of software, infrastructure, and runtime behavior for AI coding agents. The map records where each fact came from and whether it was extracted, observed, inferred, or possibly outdated.

Use them when modifying NEAT or its governed code, documentation, contracts, hooks, semantic graph, MCP or REST interfaces, or runtime tracing and provenance logic.

They tell agents which project contracts must be followed and provide fuller system context, reducing changes based on incomplete file searches or assumptions.

How neat-technologies/neat configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to neat-technologies/neat. 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/neat-technologies/neat/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/neat-technologies/neat

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/neat-technologies/neat/claude-md/github.svg)](https://agentmods.dev/instructions/neat-technologies/neat/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/neat-technologies/neat/claude-md"><img src="https://agentmods.dev/badge/instructions/neat-technologies/neat/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/neat-technologies/neat/claude-md"><img src="https://agentmods.dev/badge/instructions/neat-technologies/neat/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,039 This file is loaded in full into every session.

When invoked 1,039 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01039	$0.01039
Opus 5.5	$0.00416	$0.00416
Sonnet 5.5	$0.00208	$0.00208
Haiku 4.5	$0.00104	$0.00104

Measured 26d ago against content hash 6429ccb4b86c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

neat 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 26d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Agent guide for the NEAT repo. Read this first if you're a fresh Claude session or a human picking this up cold.

Binding rules

@docs/contracts.md is the index, auto-loaded with this file. Per-topic contracts live under docs/contracts/ and are surfaced automatically when you edit a governed file (PreToolUse hook at docs/contracts/_hook.sh, wired in .claude/settings.json). If you write code that conflicts with a contract, stop. The conflict is the bug.

What NEAT is

Agents are not good at investigation, and they are not good at reasoning. With the correct context, they are great at code and application. NEAT does the investigation and the reasoning so the agent can focus on what it's good at.

The incident card (ADR-221, docs/contracts/incident-card.md) is the clearest expression of that: one work order per incident, carrying the locus, the root-cause chain, the blast radius, the governing policies and the divergences, each claim provenance-stamped, so the agent's work starts at the fix rather than at the search.

How NEAT investigates: it keeps a live semantic graph of a software system — code, infrastructure, and runtime behavior fused into one model, queryable over MCP and a REST API. The graph carries provenance on every edge: EXTRACTED from source, OBSERVED from OpenTelemetry, INFERRED where the trace stitcher bridges gaps, STALE when runtime stops speaking, and FRONTIER for a staged proposal — so the agent knows how much to trust each claim. The card, root cause, blast radius, policy checks and divergence are all questions answered from that graph. The graph is the mechanism; the investigation it replaces is the point. (The README is the canonical, user-facing statement of what NEAT is; this section is its contributor-facing twin.)

The extraction pipeline reads static code via tree-sitter (JavaScript, TypeScript and Python in depth, symbol grain across more languages) and ingests live OTel spans to build and maintain the graph.

Read the full file on GitHub · 55 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.

26d ago Changed · +40 tokens per session 6429ccb4b86c
29d ago Changed · +4 lines · +90 tokens per session ff5c987c32fe
2mo ago First seen · 51 lines · 909 tokens per session scan A 8209c5442c0f

Subscribe to this mod's changes

neat CLAUDE.md is an instructions file published in the GitHub repository neat-technologies/neat (21 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,039 tokens to every session, about $0.0042 per session on Opus 5.5. 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.

ai-agents architecture graph-theory opentelemetry platform-engineering software-engineering

neat CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
neat CLAUDE.mdneat-technologies/neat	Instructions file	21	yesterday	Apache-2.0	A	1,039	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	3d ago	MIT	A	4,313	Codex, OpenCode

neat: Instructions file for Claude Code