What is meteor CLAUDE.md?

Project instructions describing Meteor, a tool that collects metadata from data stores and services, transforms it, and sends it to catalog systems.

Useful when working on Meteor extractors, processors, sinks, records, ownership links, data lineage, or Compass integration.

They give a coding agent the project’s architecture, data model, directories, and integration details so it can make informed changes.

meteor CLAUDE.md — Instructions file by raystack

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 instructions/raystack/meteor/claude-md

Clone the repo

git clone --depth 1 https://github.com/raystack/meteor

Per session 600 This file is loaded in full into every session.

When invoked 600 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00600	$0.00600
Opus 5	$0.00300	$0.00300
Sonnet 5	$0.00120	$0.00120
Haiku 4.5	$0.00060	$0.00060

Measured 2d ago against content hash 512268f68742, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meteor 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 2d 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 · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meteor

Meteor is a plugin-driven metadata collection agent. It extracts metadata from data stores/services via extractors, transforms it via processors, and pushes it to catalog services via sinks.

Architecture

Recipe (YAML) → Extractor → Processor(s) → Sink(s)

Each extractor emits Records. A Record contains:

Entity: urn, type, name, description, source, properties (flat structpb.Struct)
Edges: list of relationships, each with source_urn, target_urn, type, source, properties

Ownership is represented as edges with type owned_by. Lineage is represented as edges with type derived_from (entity depends on target) and generates (entity produces target).

Extractors: 35 plugins (bigquery, postgres, kafka, github, etc.)
Processors: Transform/enrich records in-flight
Sinks: Push to destinations (compass, kafka, file, http, etc.)
Runner: Orchestrates the pipeline with batching, retries, concurrency

Key Directories

models/          Core data model (Record wrapping Entity + Edges)
plugins/
  extractors/    Source plugins (one dir per source)
  processors/    Transform plugins
  sinks/         Destination plugins (compass, kafka, file, etc.)
runner/          Pipeline orchestration (batching, retries, concurrency)
recipe/          Recipe parsing and validation
cmd/             CLI commands (run, lint, list, info, gen)
docs/            Documentation site (Chronicle; content in docs/content/docs/)

Data Model

Entity (meteorv1beta1.Entity):

urn - Unique resource name
type - Entity type (table, dashboard, topic, job, user, repository, team, bucket, application, model, etc.)
name - Human-readable name
description - Description
source - Source system (e.g. bigquery, postgres, kafka)
properties - Flat key-value map (structpb.Struct) holding all type-specific metadata

Edge (meteorv1beta1.Edge):

source_urn - URN of the source entity
target_urn - URN of the target entity
type - Relationship type (owned_by, derived_from, generates, references, member_of, etc.)
source - Source system
properties - Additional metadata

Read the full file on GitHub · 64 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.

2d ago First seen · 64 lines · 600 tokens per session scan A 512268f68742

Subscribe to this mod's changes

meteor CLAUDE.md is an instructions file published in the GitHub repository raystack/meteor (242 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 600 tokens to every session, about $0.0030 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 2026-08-30.

Data and AI Planning active-metadata ai-agents context-engine context-engineering context-graph

meteor CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Meteor

Architecture

Key Directories

Data Model

What this file has done since we first saw it

Other instructions, from other repositories

compass CLAUDE.md

open-index CLAUDE.md

perseus AGENTS.md

cocoindex AGENTS.md

apm python.instructions.md

plur CLAUDE.md