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/googlecloudplatform/cortex-framework/generate_er_diagramnpx skills add GoogleCloudPlatform/cortex-framework --skill generate_er_diagramgit clone --depth 1 https://github.com/GoogleCloudPlatform/cortex-frameworkWhat 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 | $0.00034 | $0.01017 |
| Opus 5 | $0.00017 | $0.00508 |
| Sonnet 5 | $0.00007 | $0.00203 |
| Haiku 4.5 | $0.00003 | $0.00102 |
Grade A, and why
generate-er-diagram 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generating Entity-Relationship (ER) Diagrams
This skill allows agents to automatically generate clean, structured Entity-Relationship (ER) diagrams from one or more Cortex data products. The diagrams represent data models, primary keys, and relationships inferred from the data product's manifest, annotations, and definitions.
Core Operating Behaviors
When asked to generate an ER diagram for a data product:
-
Establish Output Format (CRITICAL):
- You MUST check if the user has specified the desired format for the ER diagram (e.g.,
dot,mermaid,draw.io, orall). - If the format is not specified, you MUST explicitly ask the user:
"Which format would you like to use for the ER diagram?
- Mermaid diagram (.mmd) - Best for quick markdown integration (also creates a .md file for immediate visual preview)
- Graphviz dot notation (.dot) - Best for custom graph rendering
- draw.io XML (.drawio) - Best for importing directly into draw.io as an interactive layout
- All formats - Generates Mermaid, DOT, and draw.io diagrams concurrently"
- Wait for the user's choice before executing the generator.
- You MUST check if the user has specified the desired format for the ER diagram (e.g.,
-
Locate target data product:
- Determine the name or folder of the data product to analyze. If it is not specified, look inside
src/data_modules/<namespace>/<source>/products/for available products.
- Determine the name or folder of the data product to analyze. If it is not specified, look inside
-
Execute the generator script:
- Use the virtualenv Python interpreter to run the tool:
cortex-framework-core/.venv/bin/python external-skills/.agents/skills/generate_er_diagram/scripts/generate_er_diagram.py -p <data_product_path_or_name> -f <mermaid|dot|drawio> [options] - Optional Flags:
--include-siblings: Include sibling data products in the same namespace to map cross-product relationships. (Disabled by default to prevent oversized diagrams).--all-foundation-fields: Render all fields for foundation tables (by default only keys and relationship-participating fields are shown to avoid clutter).--all-data-product-fields: Render all fields for data product tables (by default only keys and relationship-participating fields are shown to avoid clutter).
- Note: If the user selects All formats, execute the generator command three times sequentially, once for each format option (
mermaid,dot,drawio).
- Use the virtualenv Python interpreter to run the tool:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 69 lines · 34 tokens per session scan A b13931966929
generate-er-diagram is a skill published in the GitHub repository GoogleCloudPlatform/cortex-framework (10 stars, last pushed 7d ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,017 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
agent-platform-deploy
Deploy open models or custom weights from Model Garden to Agent Platform endpoints, check the status of an in-progress deployment operation, or clean up resources by undeploying models and deleting endpoints. Use when asked to actively deploy a model, list the Model Garden CATALOG of available models, check if a…
agent-platform-tuning
Agent Platform Model Tuning. Use when you need to fine-tune open models or Gemini models using Agent Platform infrastructure. Don't use for model training outside Agent Platform, model deployment to endpoints (use agent-platform-deploy), or managing serving endpoints (use agent-platform-endpoint-management).
application-design-center-design-deploy
Processes GCP infrastructure design and deployment workflows within Application Design Center (ADC). Use when: - Designing GCP infrastructure with Terraform. - Validating local HCL. - Performing best-practice plan scans. - Importing templates to Application Design Center (ADC). - Deploying templates. - Troubleshooting…
cloud-run-basics
Manages Cloud Run services, jobs, and worker pools. Use when you need to deploy applications responding to HTTP requests (services), run event-triggered or scheduled tasks (jobs), or handle always-on pull-based background processing (worker pools).
gcloud
Provides safety-critical validation, guardrails, and data reduction for gcloud CLI operations across Google Cloud Platform (GCP) services and infrastructure. Use when planning, generating, constructing, proposing, describing, or executing any gcloud CLI commands - including when answering questions about gcloud…
gemini-agents-api
Manages custom Agent resources on Gemini Enterprise Agent Platform. Use when the user wants to programmatically create, configure, list, update, or delete stateful, server-managed Agent resources (including mounting files, skills, and tools) before executing conversations.