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 orchestra-hq/orchestra-skills --skill dbt-core-airflow-to-orchestragit clone --depth 1 https://github.com/orchestra-hq/orchestra-skillsWrote 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/orchestra-hq/orchestra-skills/dbt-core-airflow-to-orchestra)<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/dbt-core-airflow-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/dbt-core-airflow-to-orchestra/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/orchestra-hq/orchestra-skills/dbt-core-airflow-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/dbt-core-airflow-to-orchestra.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 | $0.00137 | $0.02795 |
| Opus 5 | $0.00068 | $0.01398 |
| Sonnet 5 | $0.00027 | $0.00559 |
| Haiku 4.5 | $0.00014 | $0.00280 |
Grade A, and why
dbt-core-airflow-to-orchestra 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 12d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dbt Core: Airflow → Orchestra Conversion
Overview
In Airflow, dbt Core is typically run via:
BashOperatorexecutingdbt run/dbt build/ etc.SSHOperatorSSH-ing into a remote server that runsdbt run/dbt build/ etc.KubernetesPodOperatorrunning a dbt Docker image- Astronomer Cosmos (
DbtTaskGroup,DbtRunOperator, etc.)
In Orchestra, dbt Core is a first-class integration. A single Execute task under DBT_CORE replaces one or more Airflow tasks. Orchestra pulls the dbt project from a connected Git repository and runs the commands you specify.
This applies no matter which operator wrapped the dbt call in Airflow. If the task body is a dbt CLI command (dbt run, dbt build, dbt test, dbt seed, dbt snapshot), convert it to DBT_CORE_EXECUTE — even if it arrived via SSHOperator against a remote dbt server. Don't fall back to a literal LINUX_SSH translation (see airflow-bash-ssh-to-orchestra) just because the source operator happens to be SSH-based; the SSH-server detail is an Airflow deployment artifact, not something to preserve. Point the converted task at an Orchestra dbt Core connection (Git repo + warehouse credentials) instead of the SSH connection.
Parameter Mapping
BashOperator with dbt CLI
| Airflow / shell concept | Orchestra YAML field | Notes |
|---|---|---|
bash_command (the dbt command string) |
parameters.commands |
Semicolon-separated list of dbt CLI commands |
| Python version in environment | parameters.python_version |
e.g. '3.12' |
| pip / poetry / uv | parameters.package_manager |
PIP, POETRY, or UV — infer from visible project files (poetry.lock/pyproject.toml → POETRY, uv.lock → UV, requirements.txt/Pipfile → PIP) or explicit invocations (poetry run dbt ..., uv run dbt ...). If none of that is visible, don't silently guess PIP — see Gotchas |
| Git repo + branch (where dbt project lives) | connection: |
Orchestra dbt Core connection (stores Git repo URL + credentials) |
--project-dir |
parameters.project_dir |
Subdirectory within the repo where dbt_project.yml lives — a real task parameter, not connection config. Leave null if the project is at the repo root; set it for monorepos (e.g. dbt/ or analytics/dbt_project) |
--profiles-dir / profiles.yml |
Configured on Orchestra connection | Set the warehouse connection on the dbt Core connection in Orchestra |
--select / --exclude |
Include in parameters.commands |
e.g. dbt build --select models/marts |
--target |
Include in command or set on connection | e.g. dbt run --target prod |
task_id |
name: |
Human-readable task name |
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.
- 12d ago First seen · 181 lines · 137 tokens per session scan A 4c49951e2f55
dbt-core-airflow-to-orchestra is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed 3d ago), licensed MIT. It adds 137 tokens to every session and 2,795 once invoked, about $0.0007 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
pinecone
Managed vector DB for production RAG and search.
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms.
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.
ingesting-into-data-lake
Import data into the AWS data lake from S3 files, local uploads, JDBC databases (Oracle, SQL Server, PostgreSQL, MySQL, RDS, Aurora), Amazon Redshift, Snowflake, BigQuery, DynamoDB, or existing Glue catalog tables (migration). Default target is S3 Tables; standard Iceberg on a general purpose bucket is supported where…
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.