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 skills add wsauret/flywheel --skill astronomer-airflowgit clone --depth 1 https://github.com/wsauret/flywheelWrote 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/wsauret/flywheel/astronomer-airflow)<a href="https://agentmods.dev/skills/wsauret/flywheel/astronomer-airflow"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/astronomer-airflow/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/wsauret/flywheel/astronomer-airflow"><img src="https://agentmods.dev/badge/skills/wsauret/flywheel/astronomer-airflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.01609 |
| Opus 5 | $0.00028 | $0.00805 |
| Sonnet 5 | $0.00011 | $0.00322 |
| Haiku 4.5 | $0.00006 | $0.00161 |
Grade A, and why
astronomer-airflow 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 10d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Airflow 3.x on Astronomer
Operational reference for developing, running, and debugging Airflow 3.x DAGs in an Astronomer-managed local environment.
Project-specific config: If the project has a
references/repo-config.mdalongside this skill, read it first for Makefile targets, environment setup, file layout conventions, and other repo-specific details.
Environment Lifecycle (Astro CLI)
| Action | Command |
|---|---|
| Start | astro dev start |
| Stop | astro dev stop |
| Restart | astro dev restart |
| Kill (full teardown) | astro dev kill |
| Run Airflow CLI commands | astro dev run <subcommand> |
| Run pytest inside container | astro dev run pytest tests/ -v |
Default UI: http://localhost:8080 (credentials: admin / admin)
Port Conflicts
If port 8080 is already in use, stop the conflicting service first. Astro doesn't support custom webserver ports cleanly.
If port 5432 conflicts with a local Postgres, configure an alternate port in .astro/config.yaml.
DAG Development
DAG Decorator Pattern (Airflow 3.x)
from pathlib import Path
from airflow.sdk import dag
from pendulum import datetime
@dag(
dag_id=Path(__file__).stem, # Use filename as DAG ID
start_date=datetime(2025, 1, 1, tz="UTC"),
schedule=None,
catchup=False,
doc_md=__doc__, # Module docstring as docs
tags=["example"],
)
def my_pipeline() -> None:
...
my_pipeline() # Must be called at module bottom
Key points:
- Import
dagfromairflow.sdk, notairflow.decorators - Always call the decorated function at module level so Airflow discovers it
- Use
Path(__file__).stemfordag_idto keep IDs in sync with filenames
.airflowignore
Airflow respects .airflowignore files in the dags/ directory to exclude paths from DAG parsing. If a DAG doesn't appear in the UI or dags list, check this file first.
DAG Loading and Reserializing
After creating or modifying a DAG:
- Wait ~15 seconds for the scheduler to pick it up
- Or force a reparse:
astro dev run dags reserialize - Verify it loaded:
astro dev run dags list | grep <dag_name> - Check for errors:
astro dev run dags list-import-errors
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.
- 10d ago First seen · 228 lines · 56 tokens per session scan A 06df20a5c681
astronomer-airflow is a skill published in the GitHub repository wsauret/flywheel (14 stars, last pushed 6d ago), licensed MIT. It adds 56 tokens to every session and 1,609 once invoked, about $0.0003 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 skills, from other repositories
mcp-builder
Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.
domain-modeling
Build or sharpen a project's domain language and durable decisions. Use when terminology is fuzzy or contradictory, relationships need scenario testing, the code disagrees with the stated model, or a glossary or ADR-class decision must be updated; do not trigger merely to read existing context.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
recording
Capture screen recordings and screenshots on any registered computer (macOS, Windows, Linux, HarmonyOS) and manage the recording library.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
document
Skill "document" from Hmbown/Codewhale, covering document, when to use, non-goals and workflow.