What is prefect-flow-structure-to-orchestra?

A conversion guide for moving Prefect workflows—Python programs that run scheduled data or automation tasks—into Orchestra YAML, a configuration format for Orchestra pipelines.

Use it when converting Prefect flow-level configuration into Orchestra pipeline settings.

It prevents flow settings such as schedules, retries, timeouts, inputs, and deployments from being copied into the new format incorrectly.

prefect-flow-structure-to-orchestra — Skill by orchestra-hq

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-flow-structure-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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/prefect-flow-structure-to-orchestra/github.svg)](https://agentmods.dev/skills/orchestra-hq/orchestra-skills/prefect-flow-structure-to-orchestra)

Your own site

<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/prefect-flow-structure-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/prefect-flow-structure-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/prefect-flow-structure-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/prefect-flow-structure-to-orchestra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,707 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.

Model	Per session	Once invoked
Fable 5.1	$0.00102	$0.01707
Opus 5.5	$0.00041	$0.00683
Sonnet 5.5	$0.00020	$0.00341
Haiku 4.5	$0.00010	$0.00171

Measured 21d ago against content hash 03656bd6ea17, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prefect-flow-structure-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 21d 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-flow-structure-to-orchestra/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

This skill handles conversion of Prefect @flow-level constructs into Orchestra pipeline root fields. Apply it first, before converting individual tasks. It covers scheduling, retries, timeouts, typed parameters, tags, concurrency, and deployment config.

Parameter Mapping

Prefect construct	Orchestra field	Notes
`@flow(name="my-flow")`	`name: my-flow`	kebab-case recommended
`CronSchedule(cron="0 2 * * *", timezone="UTC")`	`schedule: [{cron: "0 2 * * ? *", timezone: UTC}]`	Prefect's cron is standard 5-field — convert to Orchestra's 6-field AWS EventBridge cron, do NOT copy verbatim
`IntervalSchedule(interval=timedelta(hours=6))`	`schedule: [{cron: "0 /6 * ? *"}]`	Non-clean intervals → MANUAL note
`RRuleSchedule(...)`	MANUAL note	No rrule support in Orchestra
`def my_flow(env: str = "prod")`	`inputs: {env: {type: string, default: prod}}`	int/float→number, str→string, bool→boolean
`@flow(retries=2, retry_delay_seconds=300)`	`configuration: {retries: 2, retry_delay: 5}`	Orchestra's `retry_delay` is MINUTES — convert seconds/60 (round up); cap at 120 — clamp and flag if larger
`@flow(timeout_seconds=3600)`	`configuration: {timeout: 3600}`
tag-based concurrency limit	`configuration: {concurrency: {max_active: 1, on_limit: QUEUE}}`	Prefect queues runs that hit a tag limit, so set `on_limit: QUEUE` — Orchestra's default `SKIP` would drop them. `QUEUE_LATEST` only if just the latest run matters. + MANUAL note: Prefect's limit is per tag across flows; Orchestra's is per pipeline + environment (+ branch)
`@flow(log_prints=True)`	drop	No equivalent; omit
`@flow(tags=["elt"])`	`tags: [elt]` on each task individually (NOT on the group — `TaskGroupModel` has no `tags` field)
`SecretStr` params	→ `prefect-secrets-to-orchestra`	never inline

Orchestra YAML Structure

version: v1
name: nightly-elt
schedule:
  - cron: '0 2 * * ? *'
    timezone: UTC
configuration:
  retries: 2
  retry_delay: 5
  timeout: 3600
inputs:
  target_env:
    type: string
    default: prod
  row_limit:
    type: number
    default: 0
    optional: true
pipeline:
  # ... tasks with tags: [elt]

Read the full file on GitHub · 125 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.

21d ago Changed 03656bd6ea17
2mo ago First seen · 125 lines · 102 tokens per session scan A 60ee3e239ec4

Subscribe to this mod's changes

prefect-flow-structure-to-orchestra is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed yesterday), licensed MIT. It adds 102 tokens to every session and 1,707 once invoked, about $0.0004 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 2026-08-31.

DevOps and cloud

prefect-flow-structure-to-orchestra next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
prefect-flow-structure-to-orchestraorchestra-hq/orchestra-skills	Skill	9	yesterday	MIT	A	102	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code