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 immune-profilinggit 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/immune-profiling)<a href="https://agentmods.dev/skills/inflexa-ai/inflexa/immune-profiling"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/immune-profiling/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/immune-profiling"><img src="https://agentmods.dev/badge/skills/inflexa-ai/inflexa/immune-profiling.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 | $0.00036 | $0.02309 |
| Opus 5 | $0.00018 | $0.01154 |
| Sonnet 5 | $0.00007 | $0.00462 |
| Haiku 4.5 | $0.00004 | $0.00231 |
Grade A, and why
immune-profiling 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 today.
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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Immune Profiling
This skill guides immune cell quantification, immune signature assessment, and tumor microenvironment characterization from omics data. Applicable to both bulk and single-cell modalities.
Method Selection Decision Tree
Choose the method based on input data and analytical goal:
-
Immune cell composition from bulk expression
- Use deconvolution to estimate immune cell fractions from bulk
RNA-seq or microarray. See
references/immune-deconvolution.mdfor API patterns and method selection. - Method selection:
- MCP-counter: robust marker-based scores (not fractions). Best for comparing across samples. Fast, no reference required.
- xCell: enrichment-based, 64 cell types including stroma. Good for broad profiling. Returns enrichment scores, not fractions.
- EPIC: constrained least squares. Returns absolute fractions that sum to 1. Includes "other cells" category.
- quanTIseq: designed for tumor deconvolution. Returns absolute fractions. Includes 10 immune cell types.
- CIBERSORTx: not available here. Its source and the LM22
signature matrix are distributed only through a registered,
licensed download from the Alizadeh lab site, which needs both
an account and network egress.
immunedeconvexposes acibersortmethod, but it errors unless you have already placed those licensed files on disk. Do not plan around it and do not report it as attempted — pick from the methods above.
- When to use multiple methods: Always run at least 2 methods and compare. Concordant results across methods strengthen conclusions. Report discordances.
- Use deconvolution to estimate immune cell fractions from bulk
RNA-seq or microarray. See
-
Immune cell composition from single-cell
- Cell type annotation is the primary method — no deconvolution needed. Use canonical immune markers for annotation.
- For pseudobulk comparison: aggregate single-cell data by sample, compute cell type proportions, then compare across conditions.
- For cell state analysis: subclustering within immune populations (e.g., CD8+ T cell exhaustion states).
What ships with it
2 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.
- today First seen · 195 lines · 36 tokens per session scan A a16281ef9cee
immune-profiling is a skill published in the GitHub repository inflexa-ai/inflexa (33 stars, last pushed yesterday), licensed Apache-2.0. It adds 36 tokens to every session and 2,309 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 2026-09-09.
Other skills, from other repositories
spatial-deconv
Load when deconvolving spot-level cell-type proportions on a Visium-style spatial AnnData using a labelled scRNA reference (FlashDeconv / Cell2location / RCTD / DestVI / Tangram / others). Skip when each spot is a single cell already (Xenium / MERFISH) (use spatial-annotate); tissue-domain detection (use…
bulkrna-deconvolution
Load when estimating cell-type proportions in bulk RNA-seq samples from a single-cell or signature-matrix reference. Skip when the data is already single-cell (no deconvolution needed); spatial deconvolution (use spatial-deconv).
bulkrna-trajblend
Load when placing bulk RNA-seq samples on a single-cell reference's pseudotime axis (NNLS deconvolution + nearest-neighbour mapping). Skip when plain cell-type proportions (use bulkrna-deconvolution); native single-cell trajectory inference (use sc-pseudotime).
precision-bio-tests
Expert guide for testing bioinformatics MCP servers. Covers pytest, DRYRUN modes, and PatientOne simulation scenarios.
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.