agent-toolkit CLAUDE.md

agent-toolkit CLAUDE.md is an instructions file for coding agents from atlanhq/agent-toolkit. It costs 678 tokens per session, scanned A, original, MIT.

Instructions for using Atlan, a data-management service that helps teams find, understand, track, and govern data assets.

In plain words
What is it for?
Use them to search data assets, trace where data comes from or goes, inspect ownership and metadata, and update supported asset information.
Why use it?
They explain how to authenticate and use Atlan's search, discovery, lineage, and asset-management tools from Claude Code.

Instructions file

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/atlanhq/agent-toolkit/claude-md
Clone the repo
git clone --depth 1 https://github.com/atlanhq/agent-toolkit

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 agent-toolkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/atlanhq/agent-toolkit/claude-md.svg)](https://agentmods.dev/instructions/atlanhq/agent-toolkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/atlanhq/agent-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/atlanhq/agent-toolkit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 678 This file is loaded in full into every session.
When invoked 678 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.

ModelPer sessionOnce invoked
Fable 5 $0.00678 $0.00678
Opus 5 $0.00339 $0.00339
Sonnet 5 $0.00136 $0.00136
Haiku 4.5 $0.00068 $0.00068

Measured 4d ago against content hash 7a02182270de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-toolkit 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 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.

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 · 57 lines

How it starts

The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Atlan Plugin for Claude Code

You have access to Atlan's context layer through MCP tools. The Atlan MCP server connects via OAuth at mcp.atlan.com/mcp - no API keys required. Use these tools to help users search, explore, govern, and manage their data assets.

Authentication

The Atlan MCP server uses OAuth 2.1 authentication. Users authenticate via the /mcp command in Claude Code, which opens a browser-based login flow. No API keys or environment variables are needed.

Available MCP Tools

12 tools are enabled by default for most customers. 3 additional tools are available but require enablement per tenant via feature flags.

Search & Discovery

  • semantic_search_tool - Natural language search across all data assets using AI-powered semantic understanding.
  • search_assets_tool (not enabled by default) - Search assets using structured filters and conditions.
  • get_assets_by_dsl_tool (not enabled by default) - Query assets using Atlan's DSL (Domain Specific Language) for advanced filtering.

Lineage

  • traverse_lineage_tool - Trace data flow upstream (where data comes from) or downstream (where data goes).

Asset Management

  • update_assets_tool - Update asset descriptions, certificates, README, terms, or custom metadata.

Query

  • query_assets_tool (not enabled by default) - Execute SQL queries against connected data sources.

Glossary

  • create_glossaries - Create new glossaries.
  • create_glossary_terms - Create terms within glossaries.
  • create_glossary_categories - Create categories within glossaries.

Data Mesh

  • create_domains - Create data domains and subdomains.
  • create_data_products - Create data products linked to domains and assets.

Data Quality

  • create_dq_rules_tool - Create data quality rules (null checks, uniqueness, regex, custom SQL, etc.).
  • update_dq_rules_tool - Update existing DQ rules.
  • schedule_dq_rules_tool - Schedule DQ rule execution with cron expressions.
  • delete_dq_rules_tool - Delete DQ rules.

Read the full file on GitHub · 57 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 · 57 lines · 678 tokens per session scan A 7a02182270de

Subscribe to this mod's changes

agent-toolkit CLAUDE.md is an instructions file published in the GitHub repository atlanhq/agent-toolkit (32 stars, last pushed yesterday), licensed MIT. It adds 678 tokens to every session, about $0.0034 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.