Skill Claude CodeCodex
NEAT does the investigation and the reasoning for a coding agent, so the agent can spend its effort on the code. Agents are weak at investigating a system and reasoning about its behaviour; given the right context, they are strong at writing the change. The clearest example is the incident card: when something fails…
Plugin Claude Code
Bundles 1 skill · 14 tokens together
NEAT's live semantic graph in Claude Code — the MCP graph tools, the graph-first search-nudge hook, and the skill, in one install.
MCP server Claude CodeCodexCursor +2
Fused graph of your codebase — static code + runtime OTel — for AI agents, over MCP. Runs locally from the @neat.is/mcp npm package. Needs 1 environment variable to run.
Skill Claude CodeCodex
/neat extend is a set of six MCP surgical tools for long-tail instrumentation — three diagnostic (read-only), three operative (file-scope-restricted, idempotent, reversible, observable). The user's MCP agent reasons; NEAT operates. NEAT holds no LLM key and never auto-applies. No standalone CLI variant. Discovery is…