Agent Plugins Marketplace
← All plugins

scientific-method

v1.4.28

Use when debugging, investigating root causes, designing experiments, or performing scientific analysis — enforces hypothesis-driven reasoning, evidence-first observation, causality validation, and structured output templates. Use when facing unknowns, repeated failures, or complex investigations requiring rigorous methodology.

CodexClaude Code3 Skills1 MCP serverstdio

By Jamie Nelson66 GitHub starsUpdated 3 hours ago

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
4 skill or MCP entries
Source updated
Sep 24, 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 scientific-method for Codex and Claude Code

Installs for the current user
codex plugin marketplace add Jamie-BitFlight/claude_skills
codex plugin marketplace upgrade jamie-bitflight-skills
codex plugin add scientific-method@jamie-bitflight-skills

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

Compatibility: the page URL and API slug “scientific-method” remain stable.

  • Codex: scientific-method@agent-plugin-marketplace → scientific-method@jamie-bitflight-skills

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/Jamie-BitFlight/claude_skills

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

Plugin files

plugins/scientific-method/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/evidence-first-debugging/SKILL.md
├── skills/experiment-protocol/SKILL.md
├── skills/scientific-thinking/SKILL.md
└── .mcp.json

Included Skills3

evidence-first-debuggingskills/evidence-first-debugging/SKILL.md

Use when debugging software, investigating incidents, diagnosing flaky tests, or analyzing performance regressions — enforces structured observation recording with evidence IDs, causality validation, and verification gates to prevent correlation-causation pollution. Use when an agent might otherwise summarize or speculate instead of reporting observed evidence.

experiment-protocolskills/experiment-protocol/SKILL.md

Design and run controlled experiments using the experiment-registry MCP server — domain-agnostic, pluggable, mechanically enforced. Use when you need evidence that a change actually improves behaviour.

scientific-thinkingskills/scientific-thinking/SKILL.md

Use when facing unknowns, debugging without a clear cause, or making architecture decisions — enforces hypothesis-driven scientific reasoning through observation, hypothesis formulation, prediction, experiment design, and evidence-based conclusion. Use when previous attempts have failed or the problem space involves uncertainty.

MCP servers1

experiment-registrystdio
command
uv
args
run --script mcp/experiment-registry/server.py
cwd
.

Plugin manifests2

plugins/scientific-method/.codex-plugin/plugin.json
{
  "name": "scientific-method",
  "version": "1.4.28",
  "description": "Use when debugging, investigating root causes, designing experiments, or performing scientific analysis — enforces hypothesis-driven reasoning, evidence-first observation, causality validation, and structured output templates. Use when facing unknowns, repeated failures, or complex investigations requiring rigorous methodology.",
  "author": {
    "name": "Jamie Nelson",
    "url": "https://github.com/bitflight-devops"
  },
  "skills": "./skills/",
  "interface": {
    "displayName": "Scientific Method",
    "shortDescription": "Use when debugging, investigating root causes, designing experiments, or performing scientific analysis — enforces hypothesis-driven reasoning, evidence-first observation, causality validation, and structured output templates. Use when...",
    "longDescription": "Use when debugging, investigating root causes, designing experiments, or performing scientific analysis — enforces hypothesis-driven reasoning, evidence-first observation, causality validation, and structured output templates. Use when facing unknowns, repeated failures, or complex investigations requiring rigorous methodology.",
    "developerName": "Jamie Nelson",
    "category": "Developer Tools",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "defaultPrompt": [
      "Use when debugging, investigating root causes, designing experiments, or performing scientific analysis — enforces"
    ]
  },
  "mcpServers": "./.mcp.json"
}
plugins/scientific-method/.claude-plugin/plugin.json
{
  "name": "scientific-method",
  "description": "Use when debugging, investigating root causes, designing experiments, or performing scientific analysis — enforces hypothesis-driven reasoning, evidence-first observation, causality validation, and structured output templates. Use when facing unknowns, repeated failures, or complex investigations requiring rigorous methodology.",
  "version": "1.4.28",
  "author": {
    "name": "Jamie Nelson",
    "url": "https://github.com/bitflight-devops"
  },
  "mcpServers": {
    "experiment-registry": {
      "command": "uv",
      "args": [
        "run",
        "--script",
        "${CLAUDE_PLUGIN_ROOT}/mcp/experiment-registry/server.py"
      ],
      "env": {
        "CLAUDE_PROJECT_DIR": "${CLAUDE_PROJECT_DIR}"
      }
    }
  }
}

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.

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