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 python-prefect-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/python-prefect-to-orchestra)<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/python-prefect-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/python-prefect-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/python-prefect-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/python-prefect-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 | $0.00098 | $0.02512 |
| Opus 5 | $0.00049 | $0.01256 |
| Sonnet 5 | $0.00020 | $0.00502 |
| Haiku 4.5 | $0.00010 | $0.00251 |
Grade A, and why
python-prefect-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 10d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Converts Prefect @task functions into Orchestra PYTHON_EXECUTE_SCRIPT pipeline tasks. The function body already lives inline in the flow code, not in a separate repo checked out at runtime — so it maps directly to source: INLINE + parameters.code, with no Git repo or connection wiring needed unless the task genuinely needs credentials. Only use source: GIT + parameters.command when the task checks out and runs a script from an already-separate repo. Flow-level inputs become pipeline inputs: and are passed via parameters.environment_variables (a JSON string) or inlined as literals. Task decorators (retries, timeout_seconds, tags) map to configuration: and tags:.
Parameter Mapping
| Prefect construct | Orchestra field | Notes |
|---|---|---|
@task function body |
parameters.code (inline) |
Copy the body verbatim — no extraction to a file/repo needed |
top-level imports beyond the stdlib |
parameters.build_command |
e.g. build_command: 'pip install pandas' |
| Function arguments | inline literals in code, or parameters.environment_variables + pipeline inputs: |
environment_variables is a single JSON string, e.g. '{"START_DATE": "..."}', read with os.environ["KEY"] |
@task(retries=2, retry_delay_seconds=30) |
configuration: {retries: 2, retry_delay: 1} |
Orchestra's retry_delay is MINUTES — convert seconds/60 (round up); cap at 120 |
@task(timeout_seconds=300) |
configuration: {timeout: 300} |
Seconds |
@task(cache_key_fn=...) |
drop | No Orchestra equivalent |
@task(tags=["gpu"]) |
tags: [gpu] |
|
Prefect blocks inside task (e.g. SnowflakeConnector.load(...)) |
replace with os.getenv() |
Credentials via an Orchestra connection's secrets — only wire connection: if this is actually needed |
| Return value consumed downstream | set_outputs: true + client.set_output() in code (instantiate OrchestraSDK first) |
See prefect-data-passing-to-orchestra |
.submit() / wait_for=[task_a] |
depends_on: [task-001] |
Model as explicit DAG dependency |
@flow parameters |
pipeline inputs: block |
type: string/integer/boolean, optional default: |
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.
- 10d ago First seen · 168 lines · 98 tokens per session scan A e07d4ffab6c8
python-prefect-to-orchestra is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 2,512 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
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…
dd-code-generation
Use pup CLI for immediate Datadog operations or generate code for integration into applications.
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
typing-exclusion-worker
Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.