graph-first

graph-first is a skill for Claude Code, Codex from neat-technologies/neat. It costs 43 tokens per session (1,899 once invoked), scanned B, a copy of claude-skill, Apache-2.0.

A way for an AI coding assistant to query NEAT’s live semantic graph, which maps a codebase’s structure, dependencies, and observed runtime behaviour. It is intended for architecture questions and asks the assistant to use the graph before searching text files.

In plain words
What is it for?
Use it to investigate failures, trace dependencies, estimate the impact of changing a component, and compare declared relationships with runtime observations.
Why use it?
It helps identify upstream causes, downstream impact, and differences between what code declares and what running software actually uses.

Skill for Claude CodeCodex

Part of the neat plugin — 1 skill shipped together

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 skills/neat-technologies/neat/graph-first
Any agent
npx skills add neat-technologies/neat --skill graph-first
Clone the repo
git clone --depth 1 https://github.com/neat-technologies/neat

Made for: Claude Code, Codex.

Or install neat, the plugin that ships this one along with the rest of its 1 skill.

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 graph-first

README.md
[![agentmods](https://agentmods.dev/badge/skills/neat-technologies/neat/graph-first.svg)](https://agentmods.dev/skills/neat-technologies/neat/graph-first)
Your own site
<a href="https://agentmods.dev/skills/neat-technologies/neat/graph-first"><img src="https://agentmods.dev/badge/skills/neat-technologies/neat/graph-first.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,899 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin 95% copy Near-identical to another mod 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 $0.00043 $0.01899
Opus 5 $0.00022 $0.00949
Sonnet 5 $0.00009 $0.00380
Haiku 4.5 $0.00004 $0.00190

Measured 4d ago against content hash a87aa6114830, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

graph-first scanned grade B 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`~/.neat/hooks/neat-search-nudge.mjs`, wired into `~/.claude/settings.json`)
Origin

This is a copy

95% identical to claude-skill — 5 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugin/skills/graph-first/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NEAT — Claude Code skill

This skill exposes NEAT's live semantic graph to Claude Code over MCP. Once installed, Claude can ask the running NEAT daemon (neatd) about a project's services, dependencies, recent errors, and policy violations — same as any other agent NEAT supports.

What you get

Sixteen MCP tools, served by @neat.is/mcp over stdio — ten read-only graph queries plus six /neat extend tools for instrumentation. The canonical list lives in MCP_TOOL_NAMES (@neat.is/types); the server registrations are the source for every description below.

Read tools

Tool What it does
get_root_cause Trace a failing node up its dependency graph to the underlying cause. Use when something is breaking and you want the upstream culprit.
get_blast_radius List every node downstream of a node — what would break if it failed or was redeployed.
get_dependencies Transitive outgoing dependencies, BFS to depth N, each carrying distance, edge type, and provenance (EXTRACTED vs OBSERVED).
get_observed_dependencies Only the runtime (OBSERVED via OTel) outgoing dependencies — compare what code declares against what production does.
get_incident_history Recent OTel error events recorded against a node, most recent first.
get_divergences Places where the code (EXTRACTED) and production (OBSERVED) disagree, ranked by confidence × severity. The most NEAT-shaped query — reach for it on "is anything weird?"
get_graph_diff Diff a saved graph snapshot against the current live graph — added/removed/changed nodes and edges.
get_recent_stale_edges Most recent OBSERVED → STALE transitions — integrations that have gone quiet.
check_policies Inspect or dry-run the project's policy.json. Returns current violations, or violations a hypothetical action would cause.
semantic_search Search nodes by natural-language query (embedding vectors when available, substring fallback otherwise).

Read the full file on GitHub · 130 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. 4d ago First seen · 130 lines · 43 tokens per session scan B a87aa6114830

Subscribe to this mod's changes

graph-first is a skill published in the GitHub repository neat-technologies/neat (18 stars, last pushed 2d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,899 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 95% identical to claude-skill, differing in 5 lines, and is treated as a copy.

Related

Other skills, from other repositories

legacy-discovery

Reverse-engineer / discover a codebase. Works in two modes — provide EXACTLY one input: repourl (a github.com URL) clones the repo server-side and runs full static analysis, producing a System Design Document, architecture + dependency overview, and a 100-point quality score; repopath (a local directory the server can…

sarveshtalele/mcp-skills-registry · 144 tokens

architecture-diagram

Dark-themed SVG architecture/cloud/infra diagrams as HTML.

mateaix/mateclaw · 15 tokens

studio

Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.

AlpacaLabsLLC/skills-for-architects · 65 tokens

modular-skills

Build composable skill modules with hub-and-spoke loading. Use when token budget is tight.

athola/claude-night-market · 24 tokens

product-image-processor

Download, resize, and remove backgrounds from product images at scale. Use when the user asks to "process product images", batch-download images from the schedule, strip backgrounds, or standardize product photos.

AlpacaLabsLLC/skills-for-architects · 45 tokens

tool-catalog

Show the available Architecture Studio skills and their host-appropriate commands, plus Claude Code's native Architecture Studio agents. Use when the user invokes tool-catalog, asks "what can you do" or "what skills are available", or wants a directory of plugin commands. Do not use for a host's native skill-list…

AlpacaLabsLLC/skills-for-architects · 69 tokens