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 skills/atlanhq/atlan-python/generate-v9-modelsnpx skills add atlanhq/atlan-python --skill generate-v9-modelsgit 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 | $0.00021 | $0.01955 |
| Opus 5 | $0.00010 | $0.00978 |
| Sonnet 5 | $0.00004 | $0.00391 |
| Haiku 4.5 | $0.00002 | $0.00196 |
Grade C, and why
generate-v9-models scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "${STAGING_DIR}" How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate v9 Models
Generates pyatlan_v9 msgspec model files from Pkl type definitions in the atlanhq/models repo.
Usage
/generate-v9-models— Clone models@BLDX-708, generate and sync v9 models/generate-v9-models <branch>— Clone models@ instead/generate-v9-models <branch> test— Also run tests after sync/generate-v9-models test— Clone models@BLDX-708 and run tests after sync
IMPORTANT: which branch and why
Generate from BLDX-708 (models PR #1899), not master. Only BLDX-708's
PythonMsgspecRenderer.pkl emits the per-asset validate() / minimize() /
relate() methods. Generating from master silently drops those three methods
from every generated asset (~470 of them). tests_v9/unit/model/asset_methods_test.py
is a regression guard for exactly this.
Keep BLDX-708 rebased on master so the typedefs stay current — check with
git merge-base --is-ancestor origin/master BLDX-708. If BLDX-708 is a few
commits behind, review git diff BLDX-708...origin/master and port anything
material (e.g. the Entity.custom_attributes permissive-typing renderer fix,
which lands in the hand-managed entity.py — see step 4).
Instructions
1. Clone or check out the models repo
SDK_DIR="$(pwd)" # atlan-python root
MODELS_DIR="$(cd .. && pwd)/models"
BRANCH="BLDX-708" # override with first non-"test" arg
if [ -d "$MODELS_DIR" ]; then
cd "$MODELS_DIR" && git fetch origin && git checkout "$BRANCH" && git pull origin "$BRANCH"
else
git clone [email protected]:atlanhq/models.git "$MODELS_DIR" && cd "$MODELS_DIR" && git checkout "$BRANCH"
fi
Required generator fix on BLDX-708. ModelRenderer.getTypeNameFromMapping
must use .findOrNull(...) (not .find(...)) in both the customAssetTypes and
legacyAssetTypes lookups. .find throws Cannot find matching element in collection on any unresolved supertype and aborts the whole eval (only ~320 of
~670 files get written). master already uses .findOrNull; BLDX-708 regressed
it. Verify before generating:
grep -c "findOrNull((entry) -> entry.value == customType)" toolkit/src/main/pkl/ModelRenderer.pkl # expect 2
This fix belongs upstream in models#1899.
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 · 166 lines · 21 tokens per session scan C 84f49fee1659
generate-v9-models is a skill published in the GitHub repository atlanhq/atlan-python (22 stars, last pushed 5d ago), licensed Apache-2.0. It adds 21 tokens to every session and 1,955 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
vulners-api-python-sdk
Use when modifying, testing, documenting, or reviewing the Vulners Python SDK. Covers the v4 architecture (typed sync/async clients, resource namespaces, bulletin model hierarchy, unasync codegen), the preserved legacy v3 surface, uv-based tooling, the 100% branch-coverage gate, safe API-key handling, and defensive…
zapier-sdk
Zapier SDK for TypeScript. Programmatic access to 9,000+ apps on a user's behalf via Zapier's OAuth and audit layer. Use when writing code that needs to run actions in third-party apps (send an email, upsert a CRM record, look up a spreadsheet row, post to a chat) without managing per-app OAuth or vendor SDKs.…
writing-python-code
Enforces Python 3.14 code style, logging rules, type annotations, design patterns, testing strategy, and clean code principles for the appkit project. Use when writing, reviewing, or refactoring Python code, creating new modules, or adding tests.
affinity-python-sdk
Writes Python code using the Affinity SDK for CRM data access and automation.
developer-tools
CLI tools, SDKs, and developer experience patterns.
bump-dependency
Bumps a Python package dependency across Home Assistant Core integrations, regenerates core requirement files, runs verification tests and prek lint, and prepares a pull request with proper release/compare links.