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.
npx agentmods add instructions/atlanhq/atlan-python/agents-mdgit clone --depth 1 https://github.com/atlanhq/atlan-pythonWhat 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 | $0.00876 | $0.00876 |
| Opus 5 | $0.00438 | $0.00438 |
| Sonnet 5 | $0.00175 | $0.00175 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
atlan-python AGENTS.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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security
Follow these security guidelines for every change to the pyatlan SDK.
Contact
- Security Team: #bu-security-and-it on Slack
Quickstart for Agents
atlan-python (pyatlan) is Atlan's Python SDK, providing typed wrappers around the Atlan REST API. Key modules:
pyatlan/client/atlan.py—AtlanClient(PydanticBaseSettings); initialised withbase_urlandapi_key; useshttpxwithPyatlanSyncTransport/ async variant; supports impersonation viaImpersonationClient.pyatlan/client/transport.py—PyatlanSyncTransportand async variant wraphttpx.HTTPTransportwith retry logic;trust_env=Trueby default to respectHTTPS_PROXYenv.pyatlan/client/credential.py— manages credential objects (Vault-stored secrets).pyatlan/client/token.py— manages API tokens (long-lived service account keys).pyatlan/cache/— caches for tags, groups, roles, custom metadata.
Review every change for:
- API key logging —
AtlanClientholdsapi_key(set asAuthorization: Bearer <key>on every request); it must never appear in log output, error messages, or exception tracebacks; wrap allhttpxerror handling to stripAuthorizationfrom logged request details; theapi_keyfield must be excluded from any Pydantic modeldict()/model_dump()used for logging. - Impersonation token safety —
ImpersonationClientgenerates short-lived impersonation JWTs; these tokens must not be logged; the target user's identity (email/username) may be logged but not the token value. - TLS verification —
PyatlanSyncTransportmust never passverify=Falsetohttpx.HTTPTransport; if users need to use custom CA bundles, accept a path to the bundle, not aFalseflag. base_urlvalidation —base_urlis validated asHttpUrlvia Pydantic; ensure validation rejects non-HTTPS URLs in production builds (theHttpUrltype allows HTTP by default — add a validator if HTTPS is required).- Proxy credential exposure —
trust_env=TruemeansHTTPS_PROXYis honoured; proxy credentials embedded in the URL (e.g.,http://user:pass@proxy) must not be echoed in log output; strip credentials from proxy URLs before logging. - Credential object sensitivity —
CredentialClientreturns objects withusernameand potentiallypasswordfields; these must not be logged; use repr/str exclusion for credential model classes.
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.
- yesterday First seen · 51 lines · 876 tokens per session scan A 5e659e1e6e03
atlan-python AGENTS.md is an instructions file published in the GitHub repository atlanhq/atlan-python (22 stars, last pushed 4d ago), licensed Apache-2.0. It adds 876 tokens to every session, about $0.0044 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.
Other instructions, from other repositories
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.
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.
Patter AGENTS.md
Instructions for PatterAI/Patter, covering agents.md, non-negotiables (ci and reviewers block on these), before opening a pr, where things live and commits & prs.
api AGENTS.md
Instructions for vulnersCom/api, covering agents.md — using the vulners python sdk, install & authenticate, two ways to use it, 1. as a library and 2. as an mcp server.
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.
harmonyhub-py AGENTS.md
Instructions for jenreh/harmonyhub-py, covering harmonyhub-py, 1) golden rules, 2) task bootstrap pattern, 3) tooling decision matrix and 4) sop — development workflow.