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 chuancyzhang/deepseek-cowork --skill airflowgit clone --depth 1 https://github.com/chuancyzhang/deepseek-coworkWrote 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/chuancyzhang/deepseek-cowork/airflow)<a href="https://agentmods.dev/skills/chuancyzhang/deepseek-cowork/airflow"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/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/chuancyzhang/deepseek-cowork/airflow"><img src="https://agentmods.dev/badge/skills/chuancyzhang/deepseek-cowork/airflow.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 | $0.00060 | $0.00651 |
| Opus 5.5 | $0.00024 | $0.00260 |
| Sonnet 5.5 | $0.00012 | $0.00130 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
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 1mo 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Airflow Operations
Use this skill for Apache Airflow operations and troubleshooting. It follows the Astronomer Agents Airflow workflow and supports both MCP and the af CLI.
Setup
Configure the skill in Skill Center:
AIRFLOW_API_URL: Airflow webserver base URL.AIRFLOW_AUTH_TOKEN: preferred token auth.AIRFLOW_USERNAMEandAIRFLOW_PASSWORD: alternative username/password auth.AF_READ_ONLY: defaults totrue; keep enabled unless the user explicitly wants write operations.
Authentication requires either AIRFLOW_AUTH_TOKEN or AIRFLOW_USERNAME plus AIRFLOW_PASSWORD.
MCP Server
Saving the Skill configuration automatically creates, updates, and enables the managed airflow MCP entry. The separate Test Connection action starts it only when diagnostics are requested. During normal use, Cowork installs astro-airflow-mcp into the isolated Skill Python environment and starts it on demand with --transport stdio for tool discovery or calls, injecting the configured Airflow environment. No separately managed MCP daemon or system uvx installation is required.
CLI Workflow
Use the run_af script entry for direct af commands:
{
"skill_name": "airflow",
"script_name": "run_af",
"args": ["health"]
}
Common af commands:
| Intent | Command |
|---|---|
| Health check | af health |
| List DAGs | af dags list |
| Inspect DAG | af dags explore <dag_id> |
| List runs | af runs list --dag-id <dag_id> |
| Diagnose failed run | af runs diagnose <dag_id> <run_id> |
| Task logs | af tasks logs <dag_id> <run_id> <task_id> |
| Direct API discovery | af api ls |
See api-reference.md for direct REST API examples.
run_af invokes the installed Python CLI entry directly inside the same Skill sandbox, so MCP and CLI calls use the same declared dependencies and environment variables.
Safety Rules
- Default to read-only operations.
- Do not trigger DAGs, pause/unpause DAGs, clear/delete runs, or create/update/delete variables/connections unless the user explicitly confirms the exact target.
run_afblocks common write operations whileAF_READ_ONLYistrue.- Run discovery commands with dry-run first when they can create tokens or persistent config.
What ships with it
4 files 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.
- 1mo ago First seen · 66 lines · 60 tokens per session scan A 8ba1c3a2a76d
airflow is a skill published in the GitHub repository chuancyzhang/deepseek-cowork (18 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 651 once invoked, about $0.0002 per session on Opus 5.5. 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
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…