prefect-data-passing-to-orchestra

prefect-data-passing-to-orchestra is a skill for Claude Code from orchestra-hq/orchestra-skills. It costs 95 tokens per session (2,201 once invoked), scanned A, original, MIT.

A migration guide for moving data between tasks in Prefect, a Python workflow tool, and Orchestra, a pipeline platform. It explains how returned values, submitted tasks, mapped tasks, and large files or tables must be handled in Orchestra.

In plain words
What is it for?
Use it when converting Prefect flows that pass return values, futures, artifacts, or mapped results between tasks. It also covers moving large DataFrames or files by passing a storage path or table name instead.
Why use it?
Prefect passes task results directly between tasks, while Orchestra requires values to be explicitly saved and referenced. This helps avoid broken conversions and makes clear that large data must use external storage.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the migrate-to-orchestra plugin — 52 skills shipped together

Good fit Use it when converting Prefect flows that pass return values, futures, artifacts, or mapped results between tasks. It also covers moving large DataFrames or files by passing a storage path or table name instead.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orchestra-hq/orchestra-skills/prefect-data-passing-to-orchestra
Install

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.

Any agent
npx skills add orchestra-hq/orchestra-skills --skill prefect-data-passing-to-orchestra
Clone the repo
git clone --depth 1 https://github.com/orchestra-hq/orchestra-skills

Made for: Claude Code.

Or install migrate-to-orchestra, the plugin that ships this one along with the rest of its 52 skills.

Wrote 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.

agentmods badge for prefect-data-passing-to-orchestra

README.md
[![agentmods](https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/prefect-data-passing-to-orchestra/github.svg)](https://agentmods.dev/skills/orchestra-hq/orchestra-skills/prefect-data-passing-to-orchestra)
Your own site
<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/prefect-data-passing-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/prefect-data-passing-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.

agentmods 80×15 button for prefect-data-passing-to-orchestra

Your own site · 80×15
<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/prefect-data-passing-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/prefect-data-passing-to-orchestra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,201 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00095 $0.02201
Opus 5 $0.00048 $0.01100
Sonnet 5 $0.00019 $0.00440
Haiku 4.5 $0.00010 $0.00220

Measured 12d ago against content hash 52b836401f23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

prefect-data-passing-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.

skills/migrate-to-orchestra/skills/prefect-data-passing-to-orchestra/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Prefect passes data between tasks implicitly via Python return values — a downstream task simply receives the upstream return value as an argument. Orchestra has no implicit data passing: inter-task values must be explicitly captured with the Orchestra SDK's set_output() — called on an instantiated OrchestraSDK client, not a bare imported function — in the upstream task, and referenced with a template expression in the downstream task. Large objects (DataFrames, files) cannot cross task boundaries at all and must be staged in external storage.

Parameter Mapping

Prefect pattern Orchestra equivalent Notes
result = task_a(); task_b(result) (small scalar/string) upstream: set_outputs: true + client.set_output('key', val); downstream: ${{ ORCHESTRA.PIPELINE_RUN_TASKS['task_a_id'].OUTPUTS['key'] }}
result = task_a.submit(); task_b(result.result()) same as above .submit() futures map 1-to-1
Large DataFrame passed to next task Stage in S3/Snowflake; pass only path/table name as output string DataFrames cannot cross Orchestra task boundaries
list_of_results = task.map(items) matrix: block on the task group See matrix example below
Prefect Artifact (observability only) Drop — Artifacts with no downstream consumer have no Orchestra equivalent
Prefect Artifact read by downstream step Capture with client.set_output() instead; Artifacts are not queryable by other Orchestra tasks
Conditional branch driven by task return value Upstream client.set_output('flag', bool_val) + downstream condition: '${{ ORCHESTRA.PIPELINE_RUN_TASKS[...].OUTPUTS["flag"] == true }}'

Orchestra YAML Structure

Scalar output capture (Python task)

parameters:
  command: 'python scripts/get_row_count.py'
  python_version: '3.12'
  set_outputs: true   # required — without this, client.set_output() calls are silently ignored

Corresponding Python script — instantiate the OrchestraSDK client and call .set_output() on it; ORCHESTRA_API_KEY is auto-injected into every PYTHON_EXECUTE_SCRIPT task's environment, no connection/secret needed for this:

Read the full file on GitHub · 179 lines

Changes

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.

  1. 12d ago First seen · 179 lines · 95 tokens per session scan A 52b836401f23

Subscribe to this mod's changes

prefect-data-passing-to-orchestra is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed 3d ago), licensed MIT. It adds 95 tokens to every session and 2,201 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.

Related

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…

google/skills · 85 tokens

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.

google/skills · 60 tokens

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.

microsoft/agent-framework · 65 tokens

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…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens