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 dagster-io-managers-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/dagster-io-managers-to-orchestra)<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/dagster-io-managers-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/dagster-io-managers-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/dagster-io-managers-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/dagster-io-managers-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 | $0.00097 | $0.01937 |
| Opus 5 | $0.00048 | $0.00968 |
| Sonnet 5 | $0.00019 | $0.00387 |
| Haiku 4.5 | $0.00010 | $0.00194 |
Grade A, and why
dagster-io-managers-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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dagster Data Passing (Outputs / IO Managers) -> Orchestra Outputs
Overview
Dagster passes data between ops/assets implicitly: an op returns a value, an IO manager persists it, and the downstream op receives it as a typed input. This is one of Dagster's core abstractions.
Orchestra has no shared in-process object space and no IO-manager layer. It uses a typed outputs system: a task explicitly sets named outputs (with set_outputs: true and the Orchestra SDK's set_output() called on an instantiated OrchestraSDK client — not a bare imported function — or automatic capture for SQL tasks), and downstream tasks or conditions reference them via ${{ ORCHESTRA.PIPELINE_RUN_TASKS['task_id'].OUTPUTS['key'] }}.
Key architectural difference: Dagster data flow is implicit and can carry arbitrary objects; Orchestra outputs are explicit and small (IDs, counts, flags). Large data is staged externally and only the reference is passed.
Pattern Mapping
| Dagster pattern | Orchestra equivalent |
|---|---|
return value consumed by downstream op |
client.set_output('return_value', value) + downstream reference |
Custom IOManager persisting to S3/warehouse |
Explicit write in the script; pass the path/table as an output |
Output(value, metadata=...) |
client.set_output('key', value) (metadata is observability only) |
| IO-manager-loaded input | Downstream task reads from S3/warehouse, or via ${{ ...OUTPUTS... }} for small values |
| Branch on a returned value | condition: expression on the downstream stage |
| Large DataFrame passed between ops | Stage in S3/Snowflake; pass only the path/table name |
Setting Outputs in a Python Task
stage-extract:
tasks:
get-row-count:
integration: PYTHON
integration_job: PYTHON_EXECUTE_SCRIPT
name: get_row_count
connection: my_python_conn_12345
parameters:
command: 'python scripts/get_row_count.py'
python_version: '3.12'
set_outputs: true # required
depends_on: []
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 · 199 lines · 97 tokens per session scan A 9e5b4496d645
dagster-io-managers-to-orchestra is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed 3d ago), licensed MIT. It adds 97 tokens to every session and 1,937 once invoked, about $0.0005 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-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
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 generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
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.