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 ma-compbio-lab/SkillFoundry --skill cwl-commandlinetool-startergit clone --depth 1 https://github.com/ma-compbio-lab/SkillFoundryWrote 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/ma-compbio-lab/skillfoundry/cwl-commandlinetool-starter)<a href="https://agentmods.dev/skills/ma-compbio-lab/skillfoundry/cwl-commandlinetool-starter"><img src="https://agentmods.dev/badge/skills/ma-compbio-lab/skillfoundry/cwl-commandlinetool-starter/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/ma-compbio-lab/skillfoundry/cwl-commandlinetool-starter"><img src="https://agentmods.dev/badge/skills/ma-compbio-lab/skillfoundry/cwl-commandlinetool-starter.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 | $0.00049 | $0.00460 |
| Opus 5 | $0.00024 | $0.00230 |
| Sonnet 5 | $0.00010 | $0.00092 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
cwl-commandlinetool-starter 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 6d 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.
What it actually says
Purpose
Run a small local CWL example end to end and use it as a starter for command-line tool wrapping.
When to use
- You need a verified local CWL example.
- You want a starter for wrapping a simple command-line tool in CWL.
When not to use
- You need cluster scheduling or production orchestration.
- You need Docker-only workflows.
Inputs
- A CWL workflow or command-line tool file
- A YAML or JSON job input file
- Optional output directory and summary path
Outputs
- The workflow output file
- A JSON run summary with the parsed CWL outputs and the rendered greeting text
Requirements
slurm/envs/workflow-languagescwltool
Procedure
- Run
python3 skills/reproducible-workflows/cwl-commandlinetool-starter/scripts/run_cwl_hello.py --message "hello from cwl" --workspace scratch/cwl/workspace --summary-out scratch/cwl/summary.json. - Inspect the
raw_summaryblock and the materializedgreeting.txt. - Use
examples/hello.cwlandexamples/hello-job.ymlas the base for a new localCommandLineTool.
Validation
cwltoolvalidates and runs successfully.- The summary records a greeting text and an output file named
greeting.txt.
Failure modes and fixes
- Missing runtime: verify
slurm/envs/workflow-languagesexists and containscwltool. - Validation failure: run
python -m cwltool --validateon the CWL file before debugging execution.
Safety and limits
- This skill disables containers and runs a local toy example only.
- Extend carefully before wrapping destructive commands or large data paths.
Provenance
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 50 lines · 49 tokens per session scan A 4da6581dfcc4
cwl-commandlinetool-starter is a skill published in the GitHub repository ma-compbio-lab/SkillFoundry (38 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 460 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
GitHub Actions CI Patterns
Use this skill when adding or debugging GitHub Actions workflows and you want repeatable CI behavior, minimal permissions, and clear failure logs.
atmos-sbom
Atmos SBOM provenance: CycloneDX and SPDX generation from vendor and Terraform evidence, coverage diagnostics, NTIA validation, and native CI workflow-artifact publication.
implementing-semgrep-for-custom-sast-rules
Write custom Semgrep SAST rules in YAML to detect application-specific vulnerabilities, enforce coding standards, and integrate into CI/CD pipelines.
CI/CD Pipeline Advanced
Expert-level CI/CD pipeline skill for test automation. Covers GitHub Actions, Jenkins, GitLab CI, Azure DevOps, parallel execution, matrix strategies, caching, artifact management, and deployment gates.
airflow-dag
Create Apache Airflow DAGs for construction data pipelines. Orchestrate ETL, validation, and reporting workflows.
devops-cloud
DevOps, cloud infrastructure, and platform engineering. Use when working with AWS, GCP, Azure, Kubernetes, Terraform, CI/CD pipelines, or infrastructure as code.