agentmods.dev

atlan-python CLAUDE.md

Security and review instructions for Atlan's Python software development kit, which connects Python programs to the Atlan service. They define rules for handling API keys, encrypted connections, proxy settings, and user-provided service addresses.

In plain words
What is it for?
Use it when changing or reviewing the Atlan Python SDK, especially its connection setup, authentication, logging, network security, or URL validation.
Why use it?
It helps prevent secret tokens from appearing in logs, unsafe encrypted connections, leaked proxy credentials, and untrusted service addresses from entering the client.

Instructions file

22 5d ago A scan 346 tokens original Apache-2.0
View the source file atlanhq/atlan-python
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/atlan-python/claude-md
Clone the repo
git clone --depth 1 https://github.com/atlanhq/atlan-python
Per session 346 This file is loaded in full into every session.
When invoked 346 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 $0.00346 $0.00346
Opus 5 $0.00173 $0.00173
Sonnet 5 $0.00069 $0.00069
Haiku 4.5 $0.00035 $0.00035

Measured 2d ago against content hash cf593fc1eb69, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

atlan-python 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 · 30 lines

What it actually says

Security

Follow these security guidelines for every change to the pyatlan SDK.

Contact

  • Security Team: #bu-security-and-it on Slack

Quickstart for Agents

pyatlan is Atlan's Python SDK. It wraps the Atlan REST API using httpx, handles API key auth, and provides typed models for all Atlan entities. Review every change for:

  • API key logging — the api_key (and impersonation tokens from ImpersonationClient) must never appear in log output or error messages; log only the base_url and response status codes.
  • verify=False in httpx transport — TLS certificate verification must not be disabled; trust_env=True is correct for proxy support.
  • Proxy credential leakage — if proxy credentials are configured via environment variables (HTTPS_PROXY), they must not be echoed in log output.
  • User-supplied URL validation — base_url must be validated as HTTPS before constructing the client.

Security Invariants

  • [MUST] api_key and impersonation tokens must never appear in log output.
  • [MUST] TLS certificate verification must not be disabled (verify=False is forbidden).
  • [MUST] base_url must be validated as HTTPS.

Review Checklist

  • api_key and impersonation tokens absent from all log output and error messages
  • verify=False not used in any httpx transport or session
  • base_url validated as HTTPS before client construction
  • All direct dependencies in pyproject.toml pinned exactly
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. 2d ago First seen · 30 lines · 346 tokens per session scan A cf593fc1eb69

Subscribe to this mod's changes

atlan-python CLAUDE.md is an instructions file published in the GitHub repository atlanhq/atlan-python (22 stars, last pushed 5d ago), licensed Apache-2.0. It adds 346 tokens to every session, about $0.0017 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.

Backend and APIsCode reviewSecurityapi-clientatlansdk
Related

Other instructions, from other repositories

sdk AGENTS.md

Instructions for zapier/sdk, covering agents.md, what this repo is, files to read before you start, when to use this sdk vs. alternatives and setup.

zapier/sdk · 2,398 tokens

sdk CLAUDE.md

Instructions for zapier/sdk, a project described as: Agent-readable docs, verified examples, and skill manifest for @zapier/zapier-sdk.

zapier/sdk · 5 tokens

notebooklm-py CLAUDE.md

Instructions for teng-lin/notebooklm-py, covering claude.md, project overview, development commands, full guide: docs/installation.md and before pushing.

teng-lin/notebooklm-py · 1,841 tokens

notebooklm-py AGENTS.md

Instructions for teng-lin/notebooklm-py, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

teng-lin/notebooklm-py · 744 tokens

skills copilot-instructions.md

Copilot instructions for microsoft/skills, covering copilot instructions for agent skills, project overview, ⚠️ fresh information first, core principles and 1. think before coding.

microsoft/skills · 2,575 tokens

contentful.js AGENTS.md

Instructions for contentful/contentful.js, covering agent guide, quick reference, sharp edges & invariants, key conventions and integration points.

contentful/contentful.js · 860 tokens