Agent Plugins Marketplace
← All plugins

bionexus-reliability

v1.0.0-rc.4

Scientific Reliability Layer & Scientific Warrant Engine for AI Agents (Warrant-First Evidence Assessment, Fail-Closed Invariants, Evidence-Capped Claims, Zero Silent Substitution).

CodexAgent Plugins9 Skills1 MCP serverstdio

By BioNexus TeamLicense: Apache-2.028 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Codex and Agent Plugins
Parsed components
10 skill or MCP entries
Source updated
Sep 1, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install bionexus-reliability for Codex

Installs for the current user
codex plugin marketplace add HERRY423/BioNexus
codex plugin marketplace upgrade bionexus-marketplace
codex plugin add bionexus-reliability@bionexus-marketplace

Paste and run these commands in a terminal with Codex. They add and refresh the bionexus-marketplace catalog, then install this plugin.

Compatibility: the page URL and API slug “bionexus-reliability-2” remain stable.

  • Codex: bionexus-reliability-2@agent-plugin-marketplace → bionexus-reliability@bionexus-marketplace

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/HERRY423/BioNexus

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/bionexus/.

Plugin files

plugins/bionexus/
├── .codex-plugin/plugin.json
├── plugin.json
├── skills/external-evidence-audit/SKILL.md
├── skills/instrument-data-to-allotrope/SKILL.md
├── skills/nextflow-development/SKILL.md
├── skills/provenance-and-audit/SKILL.md
├── skills/scientific-problem-selection/SKILL.md
├── skills/scvi-tools/SKILL.md
├── skills/single-cell-rna-qc/SKILL.md
├── skills/spatial-transcriptomics/SKILL.md
├── skills/start/SKILL.md
└── .mcp.json

Included Skills9

external-evidence-auditskills/external-evidence-audit/SKILL.md

Audit completed results from literature, database, analysis, sequence, structure, or slide capabilities, then optionally assemble an explicitly adjudicated multi-source claim assessment. Passive only; never select tools, infer evidence relationships, or make the final scientific decision.

instrument-data-to-allotropeskills/instrument-data-to-allotrope/SKILL.md

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV using native allotropy or declarative YAML mapping rules. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis.

nextflow-developmentskills/nextflow-development/SKILL.md

Prepare nf-core samplesheets, cluster nextflow.config, and write launch artifacts. nfcore_launch.py only wraps nf-core/rnaseq and nf-core/scrnaseq with optional nextflow -preview. Other pipelines still use generate_samplesheet.py plus a hand-written nextflow run. Does not reimplement the pipelines.

provenance-and-auditskills/provenance-and-audit/SKILL.md

SHA-256 hashes, environment snapshot, and activity-aware Methods text. Use to attach a reproducibility sidecar to an analysis. Do not use for 21 CFR Part 11, GxP, ALCOA+, or CLIA audit claims.

scientific-problem-selectionskills/scientific-problem-selection/SKILL.md

This skill should be used when scientists need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic scientific decisions. Use this skill when users ask to pitch a new research idea, work through a project problem, evaluate project risks, plan research strategy, navigate decision trees, or get help choosing what scientific problem to work on. Typical requests include "I have an idea for a project", "I'm stuck on my research", "help me evaluate this project", "what should I work on", or "I need strategic advice about my research".

scvi-toolsskills/scvi-tools/SKILL.md

Train official scvi-tools models (scVI/scANVI/totalVI/PeakVI/MultiVI/veloVI) on raw counts after the scRNA gold chain. Use for probabilistic batch integration or those named models. Does not run DestVI/Cell2location. Do not log-normalize before setup_anndata.

single-cell-rna-qcskills/single-cell-rna-qc/SKILL.md

scverse scRNA gold chain on .h5ad/.h5 — inspect, convert, MAD QC, optional scanpy.pp.scrublet, preprocess, Harmony/ComBat, PCA-UMAP-Leiden, Wilcoxon markers, subset, pseudobulk, pydeseq2, stable plots. Use when the user has scRNA-seq counts. Does not assign cell-type labels. rank_genes_groups is not condition DE. Do not call local doublet/ambient helpers SoupX, CellBender, or scDblFinder.

spatial-transcriptomicsskills/spatial-transcriptomics/SKILL.md

squidpy spatial gold chain on SpatialData .zarr or AnnData .h5ad with obsm['spatial']. Use when the user has Visium/Slide-seq/generic spots or cells with coordinates. Builds a knn spatial graph, Moran SVGs, and spatial_scatter plots. Multi-table SpatialData requires --table. Does not run Cell2location, BayesSpace, SpaGCN, or vendor HD/Xenium pipelines. Numeric clusters only.

startskills/start/SKILL.md

Orient a session on this plugin. Use first. Run scripts/doctor.py, then route only to core gold-chain skills unless the user names a heuristic job. Do not assign cell-type labels. Do not use this skill to run analyses.

MCP servers1

bionexus-local-mcpstdio
command
python
args
${PLUGIN_ROOT}/scripts/local_mcp_server.py --audit-log ${PLUGIN_ROOT}/.bionexus-audit/mcp-host-audit.jsonl
cwd
${PLUGIN_ROOT}

MCP configuration uses runtime-provided plugin path placeholders such as ${PLUGIN_ROOT} or ${CLAUDE_PLUGIN_ROOT}. Review the manifest for the runtime-specific expansion rules.

Plugin manifests2

plugins/bionexus/.codex-plugin/plugin.json
{
  "name": "bionexus-reliability",
  "version": "1.0.0-rc.4",
  "description": "Scientific Reliability Layer & Scientific Warrant Engine for AI Agents (Warrant-First Evidence Assessment, Fail-Closed Invariants, Evidence-Capped Claims, Zero Silent Substitution).",
  "author": {
    "name": "BioNexus Team",
    "url": "https://github.com/HERRY423/BioNexus"
  },
  "homepage": "https://github.com/HERRY423/BioNexus",
  "repository": "https://github.com/HERRY423/BioNexus",
  "license": "Apache-2.0",
  "keywords": [
    "bionexus",
    "bioinformatics",
    "single-cell",
    "scanpy",
    "scvi-tools",
    "nextflow",
    "nf-core",
    "allotrope",
    "mcp",
    "variant-interpretation",
    "spatial-transcriptomics",
    "squidpy"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "BioNexus",
    "shortDescription": "The Scientific Reliability Layer for Agentic Biology",
    "longDescription": "Scientific Reliability Layer & Scientific Warrant Engine for AI Agents (Warrant-First Evidence Assessment, Fail-Closed Invariants, Evidence-Capped Claims, Zero Silent Substitution).",
    "developerName": "BioNexus Team",
    "category": "Science",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "websiteURL": "https://github.com/HERRY423/BioNexus",
    "defaultPrompt": [
      "Audit evidence returned by another science plugin",
      "Check whether this result warrants the proposed claim",
      "Verify provenance, backend identity, and claim ceiling"
    ]
  }
}
plugins/bionexus/plugin.json
{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "bionexus-reliability",
  "version": "1.0.0-rc.4",
  "description": "Scientific Reliability Layer & Scientific Warrant Engine for AI Agents (Warrant-First Evidence Assessment, Fail-Closed Invariants, Evidence-Capped Claims, Zero Silent Substitution).",
  "author": {
    "name": "BioNexus Team"
  },
  "license": "Apache-2.0",
  "keywords": [
    "bionexus",
    "bioinformatics",
    "single-cell",
    "scanpy",
    "scvi-tools",
    "nextflow",
    "nf-core",
    "allotrope",
    "mcp",
    "variant-interpretation",
    "spatial-transcriptomics",
    "squidpy"
  ],
  "skills": "./skills/",
  "mcpServers": "./mcp.json"
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[bionexus-reliability on Agent Plugins Marketplace](https://pluginsmp.com/plugins/bionexus-reliability-2)