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 agentmods add skills/nextflow-io/agent-skills/launch-workflownpx skills add nextflow-io/agent-skills --skill launch-workflowgit clone --depth 1 https://github.com/nextflow-io/agent-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/nextflow-io/agent-skills/launch-workflow)<a href="https://agentmods.dev/skills/nextflow-io/agent-skills/launch-workflow"><img src="https://agentmods.dev/badge/skills/nextflow-io/agent-skills/launch-workflow.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.01294 |
| Opus 5 | $0.00031 | $0.00647 |
| Sonnet 5 | $0.00012 | $0.00259 |
| Haiku 4.5 | $0.00006 | $0.00129 |
Grade A, and why
launch-workflow 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 4d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch Pipeline on Seqera Platform
Launch Nextflow pipeline executions on cloud (AWS, Google Cloud, Azure) and HPC clusters (Slurm, LSF, etc.) through Seqera Platform. Seqera Platform manages the target compute environment, executes the pipeline from a remote Git repository, and provides monitoring.
Requires Nextflow 26.04 or later (for the nextflow auth and nextflow launch commands).
Main Flow
- Configure the compute environment — select a Seqera Platform compute environment for the target cloud or cluster.
- Ensure the pipeline is in a remote Git repository — Seqera Platform launches pipelines from GitHub (or a compatible Git host such as GitLab or Bitbucket). If the local pipeline is not yet hosted, assist the user in setting up the repository.
- Upload local changes — push any uncommitted local changes to the remote so the launched run reflects the user's current code.
- Launch with
nextflow launch— submit the pipeline by passing the Git repository URL and the expected parameters.
Step 1: Authenticate with Seqera Platform
Check whether the user is already authenticated:
nextflow auth status
If not authenticated, sign in:
nextflow auth login
This opens a browser for authentication. Wait for the user to complete the login flow before proceeding.
Step 2: Configure the Compute Environment
List available compute environments using the Seqera API:
call_seqera_api(
service: "platform",
api_name: "platform_list_compute_envs",
parameters: {}
)
Selecting the compute environment:
- Present the available compute environments to the user (name, platform type, region/cluster).
- If multiple environments are available, ask the user which one to use.
- If only one is available, propose it and ask for confirmation.
- Confirm the selected compute environment with the user before launching.
Step 3: Ensure the Pipeline Is in a Remote Git Repository
Seqera Platform launches pipelines from a remote Git URL — it cannot launch directly from a local path. Verify the pipeline directory is a Git repository connected to a remote on GitHub (or a compatible host like GitLab or Bitbucket).
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.
- 4d ago First seen · 149 lines · 62 tokens per session scan A 40ee0cca1679
launch-workflow is a skill published in the GitHub repository nextflow-io/agent-skills (21 stars, last pushed 29d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,294 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
modal-compute
Run explicitly chosen research benchmark or replication jobs on Modal's serverless infrastructure. Use when a Feynman research workflow needs burst remote GPU compute and the Modal CLI is available.
remote-compute-ssh
Evaluate and use SSH Remote Compute before choosing where to run GPU, high-memory, parallel, batch, model-inference, bioinformatics, or other long-running scientific work; supports short remote commands and asynchronous jobs with automatic harvest and analysis.
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
remote-compute-ssh
Run Feynman research jobs on SSH, Slurm, or lab hosts. Use when a task needs remote host setup, job submission, log harvest, artifact sync, or GPU/cluster execution outside Modal.
remote-compute-modal
Dispatch Feynman research notebook or experiment jobs to Modal. Use when a task has explicitly chosen Modal for bounded cloud compute, GPU jobs, or reproducible remote execution.
runpod-compute
Provision and manage GPU pods on RunPod for explicitly chosen long-running research experiments. Use when a Feynman replication, benchmark, or dataset-heavy research run needs persistent GPU compute with SSH access.