Borrowing it
Nothing to install: this file belongs to atlanhq/atlan-python. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/atlanhq/atlan-python/main/.claude/skills/generate-v9-models/SKILL.mdgit clone --depth 1 https://github.com/atlanhq/atlan-pythonWrote 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.
[](https://agentmods.dev/skills/atlanhq/atlan-python/generate-v9-models)<a href="https://agentmods.dev/skills/atlanhq/atlan-python/generate-v9-models"><img src="https://agentmods.dev/badge/skills/atlanhq/atlan-python/generate-v9-models/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/atlanhq/atlan-python/generate-v9-models"><img src="https://agentmods.dev/badge/skills/atlanhq/atlan-python/generate-v9-models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00021 | $0.02051 |
| Opus 5.5 | $0.00008 | $0.00820 |
| Sonnet 5.5 | $0.00004 | $0.00410 |
| Haiku 4.5 | $0.00002 | $0.00205 |
Grade C, and why
generate-v9-models scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "${STAGING_DIR}" How it starts
The opening of the file, as written. The whole thing — 172 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.
- 14d ago Changed · +6 lines 40d10a20995e
- 1mo 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 (21 stars, last pushed yesterday), licensed Apache-2.0. It adds 21 tokens to every session and 2,051 once invoked, about $0.0001 per session on Opus 5.5. 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
notebooklm
Install, authenticate, troubleshoot, and operate Gemini Notebook through the notebooklm-py CLI or typed async Python API. Use for notebook and source management, grounded chat and research, and artifact generation or download when the user mentions Gemini Notebook, notebooklm-py, the notebooklm CLI, or its Python API.…
azure-mgmt-fabric-py
Azure Fabric Management SDK for Python. Use for managing Microsoft Fabric capacities and resources. Triggers: "azure-mgmt-fabric", "FabricMgmtClient", "Fabric capacity", "Microsoft Fabric", "Power BI capacity".
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…
developing-genkit-python
Develop AI-powered applications using Genkit in Python. Use when the user asks about Genkit, AI agents, flows, or tools in Python, or when encountering Genkit errors, import issues, or API problems.
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.