Agent Plugins Marketplace
← All plugins

adaptive-optimization

v1.0.0

Run design-test-learn rounds on an antibody or protein lead optimization project: select the next batch under enforced developability constraints, reconcile assay results against the registry, and diagnose a round that came back wrong. Bundles the skill, the diagnostic library and both connectors.

Claude Code1 Skill2 MCP serversstdio

By Dylan Webster0 GitHub starsUpdated 3 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
3 skill or MCP entries
Source updated
Sep 20, 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 adaptive-optimization for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install adaptive-optimization@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

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/cooperstlogic/adaptive-workbench

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

Plugin files

adaptive-optimization/
├── .claude-plugin/plugin.json
├── skills/adaptive-optimization/SKILL.md
└── .mcp.json

Included Skills1

adaptive-optimizationskills/adaptive-optimization/SKILL.md

Run design-test-learn rounds on an antibody or protein lead optimization project - select the next batch of variants to test, import assay results, fit and compare surrogate models, score the previous round's predictions, and diagnose a round that came back wrong. Use for affinity maturation, batch selection under developability constraints, active learning over a candidate pool, and deciding what an ambiguous round of results means.

MCP servers2

bioproviderstdio
command
${CLAUDE_PLUGIN_ROOT}/.venv/bin/python
args
${CLAUDE_PLUGIN_ROOT}/connectors/bioprovider_server.py
registrystdio
command
${CLAUDE_PLUGIN_ROOT}/.venv/bin/python
args
${CLAUDE_PLUGIN_ROOT}/connectors/registry_server.py

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 manifests1

.claude-plugin/plugin.json
{
  "name": "adaptive-optimization",
  "description": "Run design-test-learn rounds on an antibody or protein lead optimization project: select the next batch under enforced developability constraints, reconcile assay results against the registry, and diagnose a round that came back wrong. Bundles the skill, the diagnostic library and both connectors.",
  "version": "1.0.0",
  "mcpServers": {
    "registry": {
      "type": "stdio",
      "command": "${CLAUDE_PLUGIN_ROOT}/.venv/bin/python",
      "args": [
        "${CLAUDE_PLUGIN_ROOT}/connectors/registry_server.py"
      ],
      "env": {}
    },
    "bioprovider": {
      "type": "stdio",
      "command": "${CLAUDE_PLUGIN_ROOT}/.venv/bin/python",
      "args": [
        "${CLAUDE_PLUGIN_ROOT}/connectors/bioprovider_server.py"
      ],
      "env": {}
    }
  },
  "author": {
    "name": "Dylan Webster"
  }
}

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.

[adaptive-optimization on Agent Plugins Marketplace](https://pluginsmp.com/plugins/adaptive-optimization)