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 bigbio/sdrf-skills --skill sdrf-designgit clone --depth 1 https://github.com/bigbio/sdrf-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/bigbio/sdrf-skills/sdrf-design)<a href="https://agentmods.dev/skills/bigbio/sdrf-skills/sdrf-design"><img src="https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-design/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/bigbio/sdrf-skills/sdrf-design"><img src="https://agentmods.dev/badge/skills/bigbio/sdrf-skills/sdrf-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.01380 |
| Opus 5 | $0.00017 | $0.00690 |
| Sonnet 5 | $0.00007 | $0.00276 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade A, and why
sdrf-design 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SDRF Experimental Design Analysis
You are analyzing the experimental design captured in an SDRF file to detect statistical and methodological issues.
Step 1: Parse the Design
Extract from the SDRF:
- Conditions: Unique values in factor value columns
- Samples per condition: Count of unique source names per condition
- Biological replicates: From characteristics[biological replicate]
- Technical replicates: From comment[technical replicate]
- Fractions: From comment[fraction identifier]
- Labels: From comment[label]
- Instruments: From comment[instrument]
- Files per sample: Count of rows per source name
Exclude non-biological channels before counting replicates or testing balance. Drop rows that are reference / carrier / bridge / empty / pooled / control —
characteristics[sample type]in {reference, bridge, carrier, empty, pooled, ...-control}, or rows carryingcomment[carrier channel](PRIDE:0000901) /comment[reference channel](PRIDE:0000899). Counting them inflates n and corrupts the TMT/label cross-tabs. Replication = uniquesource nameper condition, not raw row count.
Step 2: Design Summary
Present a clear summary:
Experimental Design Summary:
Type: Two-group comparison
Factor: disease (breast carcinoma vs normal)
Group 1 "breast carcinoma": 10 biological replicates
Group 2 "normal": 10 biological replicates
Technical setup:
Label: TMT10plex (10 channels per plex)
Fractions: 12 per TMT set
Technical replicates: 1 per sample
Instrument: Q Exactive HF
File math:
2 TMT sets × 12 fractions = 24 raw files
Each file → 10 rows (one per TMT channel)
Total SDRF rows: 240
Statistical power:
n=10 per group — adequate for detecting medium effect sizes
Step 3: Batch Effect Detection
Cross-tabulate factor values against technical variables:
Instrument Confounding
Check: Is "condition" confounded with "instrument"?
Cross-tab factor value × comment[instrument]
BAD: All "disease" on Instrument A, all "control" on Instrument B
→ Cannot separate biology from instrument effect
GOOD: Both conditions measured on both instruments (balanced)
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 Changed · -1 tokens per session 50de4513718a
- 10d ago First seen · 173 lines · 36 tokens per session scan A 84228efd3dec
sdrf-design is a skill published in the GitHub repository bigbio/sdrf-skills (18 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 1,380 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 2026-08-30.
Other skills, from other repositories
uniprot-query
Query UniProt database for protein sequences, metadata, and search by criteria. Use this skill when: (1) Looking up protein information by UniProt accession ID, (2) Searching proteins by gene name, organism, function, or disease, (3) Retrieving comprehensive protein metadata including domains, PTMs, and annotations.
proteomics-de
Load when computing two-group differential protein abundance (group2 vs group1, log2FC + p-value + BH-adjusted FDR) via Welch t-test, equal-variance t-test, or Mann-Whitney on a wide protein × sample CSV. Skip when you need multi-condition DE (run pairwise contrasts manually); label-based TMT linear-mixed models.
proteomics-enrichment
Load when running over-representation analysis (ORA) on a list of proteins via Fisher's exact test against a built-in 8-pathway DEMO dictionary, with BH-FDR correction. Skip when needing a real pathway database (this skill is demo-only) (use bulkrna-enrichment); rank-based GSEA.
proteomics-ptm
Load when summarising PTM sites (phosphorylation, acetylation, ubiquitination, etc.) from a per-site CSV — site-class assignment (Olsen et al. Class I/II/III by localizationprobability), per-PTM-type counts, amino-acid distribution, sites-per-protein. Skip when raw spectra are the input; you only need protein-level…
proteomics-quantification
Load when computing per-protein abundance from a peptide / PSM table via LFQ (intensity summation), iBAQ (intensity / tryptic peptide count), or spectral counting (PSMs per protein). Skip when the input is already protein-level (use proteomics-ms-qc); label-based TMT / iTRAQ workflows (search upstream first).
proteomics-structural
Load when summarising cross-linking MS (XL-MS) results — intra/inter-protein link split, optional FDR filtering, distance-constraint validation against a per-crosslinker (DSS / BS3 / EDC / DSSO / DSBU) max distance. Skip when raw spectra are the input (run XlinkX / pLink / xiSEARCH first); no XL-MS experiment was…