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 inflexa-ai/inflexa --skill metabolomicsgit clone --depth 1 https://github.com/inflexa-ai/inflexaWrote 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/inflexa-ai/inflexa/metabolomics)<a href="https://agentmods.dev/skills/inflexa-ai/inflexa/metabolomics"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/metabolomics/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/inflexa-ai/inflexa/metabolomics"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/metabolomics.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 | $0.00027 | $0.01954 |
| Opus 5 | $0.00014 | $0.00977 |
| Sonnet 5 | $0.00005 | $0.00391 |
| Haiku 4.5 | $0.00003 | $0.00195 |
Grade A, and why
metabolomics 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 yesterday.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Metabolomics & Lipidomics Analysis
Comprehensive guidelines for untargeted metabolomics, targeted metabolomics, lipidomics, and metabolic pathway interpretation.
Method-Selection Decision Tree
1. Untargeted Metabolomics
Raw mzML files
→ Peak picking: XCMS CentWave in R (matchedFilter for low-res data)
→ RT alignment: XCMS adjustRtime (obiwarp or peakGroups)
→ Feature grouping: XCMS groupChromPeaks (PeakDensity)
→ Gap filling: XCMS fillChromPeaks
→ Feature table (m/z x RT x intensity matrix)
- Use pymzml for raw file inspection and chromatogram extraction before peak picking.
- XCMS in R is the standard pipeline. Do NOT use Python-only peak picking unless XCMS is unavailable.
- Export the feature table as AnnData: features (m/z_RT) as
var, samples asobs, intensities asX.
2. Targeted Metabolomics
Vendor output (concentrations or peak areas)
→ Concentration extraction from quantification report
→ Standard curve validation (R^2 >= 0.99 preferred, >= 0.98 acceptable)
→ Flag values below LOD/LOQ
→ Statistical testing (same pipeline as untargeted, starting from clean matrix)
- If raw data is provided instead of vendor output, use XCMS with targeted feature extraction (known m/z + RT windows).
3. Normalization Selection
| Scenario | Method | Notes |
|---|---|---|
| Default / simple | TIC (total ion current) | Sum-normalize each sample; fast but assumes equal total metabolite load |
| Robust cross-sample | PQN (probabilistic quotient) | Reference-based quotient scaling; robust to outlier features |
| Batched runs with signal drift | LOESS | Fit local regression to QC pool injections; correct drift per feature |
| Internal standards available | IS normalization | Normalize by spiked-in standard intensity; most accurate when available |
- Apply normalization AFTER gap filling but BEFORE log transformation.
- Always log2-transform after normalization for downstream statistics.
What ships with it
3 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.
- yesterday First seen · 128 lines · 27 tokens per session scan A 448678028b0f
metabolomics is a skill published in the GitHub repository inflexa-ai/inflexa (33 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 1,954 once invoked, about $0.0001 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 2026-09-09.
Other skills, from other repositories
metabolomics-peak-detection
Load when running per-sample peak picking on a feature × intensity table via scipy.signal.findpeaks — emits per-(sample, feature) detected peaks with prominence and width. Skip when working with mz / RT raw scans (use metabolomics-xcms-preprocessing); only normalising / quantifying (use metabolomics-quantification).
metabolomics-xcms-preprocessing
Load when running an XCMS-style preprocessing summary on LC-MS metabolomics raw / vendor-converted files — emits a peak table with m/z, retention time, and per-sample intensities. Skip when working with an already-built peak table (use metabolomics-peak-detection); only annotation is needed (use…
biosymphony-structure-factory
Use when planning structural biology campaigns, binder-design triage, model comparison, structure mapping, RunPod or cloud GPU stage contracts, or Symphony or Linear task packs for long-running biological agent work.
binder-lane-round
Plan and run study-shaped protein-binder rounds with interchangeable toolchains, execution profiles, license gates, output checks, and result boundaries.
esm2
Skill for working with ESM2 protein language models from Meta FAIR. Use this skill whenever the user wants to generate protein embeddings or representations, score variant effects or predict mutation fitness, run contact prediction, or use ESMFold for structure prediction. Also trigger when the user mentions ESM2…
evo2
Skill for genomic sequence modeling and design with Evo2 from Arc Institute. Use this skill when a user wants to model or generate DNA sequences, score variant effects at single-nucleotide resolution, extract genomic embeddings, analyze mutations in non-coding or coding regions, design synthetic genomic elements…