Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ma-compbio-lab/SkillFoundrynpx agentmods add skills/ma-compbio-lab/skillfoundry/rocrate-metadata-bundle-starterWrote 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/rocrate-metadata-bundle-starter)<a href="https://agentmods.dev/skills/ma-compbio-lab/skillfoundry/rocrate-metadata-bundle-starter"><img src="https://agentmods.dev/badge/skills/ma-compbio-lab/skillfoundry/rocrate-metadata-bundle-starter.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 5.1 | $0.00000 | $0.00310 |
| Opus 5 | $0.00000 | $0.00155 |
| Sonnet 5 | $0.00000 | $0.00062 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
rocrate-metadata-bundle-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 7d 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
RO-Crate Metadata Bundle Starter
Use this skill to package a small local data file into an RO-Crate directory with basic provenance-rich metadata and a compact summary of the generated graph.
What it does
- copies one local data file into a fresh RO-Crate directory
- writes
ro-crate-metadata.jsonwith a named root dataset and measurement metadata - reports the crate path, graph entity counts, and bundled data files
When to use it
- you need a verified starter for
data-provenance-tracking - you want a lightweight pattern for packaging outputs with reusable metadata
- you need a deterministic RO-Crate fixture for tests or demos
Example
./slurm/envs/data-tools/bin/python skills/data-acquisition-and-dataset-handling/rocrate-metadata-bundle-starter/scripts/build_rocrate_metadata_bundle.py \
--input skills/data-acquisition-and-dataset-handling/rocrate-metadata-bundle-starter/examples/toy_measurements.csv \
--crate-dir scratch/rocrate/toy_bundle \
--summary-out scratch/rocrate/toy_bundle_summary.json
Verification
- Skill-local tests:
python3 -m unittest discover -s skills/data-acquisition-and-dataset-handling/rocrate-metadata-bundle-starter/tests -p 'test_*.py' - Expected summary:
has_metadata_file == true,data_entity_count == 1,root_dataset_name == "Toy Measurement Bundle"
What ships with it
8 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.
- assets/toy_bundle_summary.json 651 B
- assets/toy_bundle/ro-crate-metadata.json 1.0 KB
- assets/toy_bundle/toy_measurements.csv 70 B
- examples/toy_measurements.csv 70 B
- metadata.yaml 1.4 KB
- refs.md 224 B
- scripts/build_rocrate_metadata_bundle.py 3.4 KB runs code
- tests/test_build_rocrate_metadata_bundle.py 2.4 KB runs code
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.
- 7d ago First seen · 30 lines · 0 tokens per session scan A 6df213931249
rocrate-metadata-bundle-starter is a skill published in the GitHub repository ma-compbio-lab/SkillFoundry (38 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 310 tokens. 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
automated-soap-note-generator
Generate structured SOAP notes from clinical narratives, transcripts, or existing notes; use when the user needs de-identified clinical documentation organized into Subjective, Objective, Assessment, and Plan sections, with clear assumptions and review points.
digital-twin-discharge-drafter
Use when drafting patient discharge summaries, creating personalized discharge instructions, simulating post-discharge outcomes, reducing hospital readmissions, or optimizing care transitions. Generates AI-enhanced discharge documentation with digital twin predictions for improved patient safety.
discharge-summary-writer
Generate hospital discharge summaries from admission data, hospital course, diagnoses, procedures, and follow-up plans; use when a structured discharge document is required from clinical notes.
medical-scribe-dictation
Convert physician verbal dictation into structured SOAP notes. Trigger.
consistency-checker-across-manuscript
Checks consistency across title, abstract, methods, results, figures, tables, and supplements to identify internal contradictions and version drift in biomedical manuscripts.
latex-manuscript-format-converter
Converts existing manuscript content into LaTeX format aligned with a target journal, conference, or template while preserving manuscript meaning and structural integrity.