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/ma-compbio-lab/skillfoundry/metadata-harmonization-starternpx skills add ma-compbio-lab/SkillFoundry --skill metadata-harmonization-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/metadata-harmonization-starter)<a href="https://agentmods.dev/skills/ma-compbio-lab/skillfoundry/metadata-harmonization-starter"><img src="https://agentmods.dev/badge/skills/ma-compbio-lab/skillfoundry/metadata-harmonization-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 | $0.00000 | $0.00313 |
| Opus 5 | $0.00000 | $0.00156 |
| Sonnet 5 | $0.00000 | $0.00063 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
metadata-harmonization-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 5d 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
Metadata Harmonization Starter
Use this skill to harmonize small metadata tables with inconsistent column names and categorical labels into one canonical TSV plus a compact JSON summary.
What This Skill Does
- reads one or more tabular metadata files
- applies a JSON mapping from source columns to canonical fields
- normalizes selected categorical values such as
sexandcondition - writes a harmonized TSV and a machine-readable summary
When To Use It
- when you need a starter for
metadata-harmonization - when multiple small test fixtures use different metadata headers
- when you want deterministic harmonized outputs before validation or format conversion
Run
python3 skills/data-acquisition-and-dataset-handling/metadata-harmonization-starter/scripts/run_metadata_harmonization.py \
--input skills/data-acquisition-and-dataset-handling/metadata-harmonization-starter/examples/cohort_a.tsv \
--input skills/data-acquisition-and-dataset-handling/metadata-harmonization-starter/examples/cohort_b.tsv \
--mapping skills/data-acquisition-and-dataset-handling/metadata-harmonization-starter/examples/column_mapping.json \
--out-tsv scratch/metadata-harmonization/harmonized_metadata.tsv \
--summary-out scratch/metadata-harmonization/harmonized_metadata_summary.json
Notes
- The starter keeps the mapping external so the same script can be reused for other tiny fixtures.
- Canonical rows are sorted by
sample_idto keep committed outputs deterministic.
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.
- assets/harmonized_metadata_summary.json 688 B
- assets/harmonized_metadata.tsv 212 B
- assets/README.md 80 B
- examples/cohort_a.tsv 74 B
- examples/cohort_b.tsv 97 B
- examples/column_mapping.json 755 B
- metadata.yaml 1.6 KB
- refs.md 240 B
- scripts/run_metadata_harmonization.py 4.3 KB runs code
- tests/test_run_metadata_harmonization.py 3.1 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.
- 5d ago First seen · 33 lines · 0 tokens per session scan A c14368ce34ce
metadata-harmonization-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 313 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
grounded-review
Review a research report draft with a structured scoring rubric, run a bounded repair loop when needed, and produce the final deliverable report.
one-report
Run the full One-Report pipeline from one input file through grounding, research, evidence-rich report drafting, final review quality-gating, and export, while reusing existing skills, preserving current contracts, and enforcing strict downstream skill fidelity for every grounded unit.
grounded-research-lit
Run focused literature and web research from a grounded note. Use when a grounded note already exists and you want targeted research results, opened-link evidence, deeper per-paper analysis materials, optional downloaded literature, and a two-stage literature output (litinitial.md then refined lit.md).
grounded-summary
Create a rich, evidence-preserving research report draft from a grounded note and its follow-up literature result. This is the main report-writing stage of the middle pipeline, not a compression memo.
remote-input
Download remote content (arxiv papers, YouTube videos, Bilibili videos) to local storage and route to downstream grounding pipeline. Use when user provides a URL instead of a local file path.
skill-evolve
Optional sidecar skill for controlled feedback-driven skill evolution. Not part of the default pipeline. Only activates when explicitly requested.