agentmods.dev

research-proof-plugin

A research-planning plugin for testing whether claims are supported by evidence. It uses ideas from scientific, AI, and medical research to structure evaluations and track proof.

In plain words
What is it for?
Use it to plan research, define evaluators, challenge claims, build evidence ladders, and maintain records of what supports each conclusion.
Why use it?
It helps expose weak or unfalsifiable claims before they are treated as reliable conclusions. It keeps the evidence, tests, and certainty level organized.

Plugin for Claude Code

45 3mo ago A scan tokens not measured original MIT
View the source file tonyblu331/research-proof
Install

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.

Claude Code
/plugin marketplace add tonyblu331/research-proof
agentmods
npx agentmods add plugins/tonyblu331/research-proof/research-proof-plugin
Clone the repo
git clone --depth 1 https://github.com/tonyblu331/research-proof

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

research-proof-plugin 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 2d ago.

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.

plugins/research-proof-plugin/.claude-plugin/plugin.json · 30 lines

What it actually says

{
  "name": "research-proof-plugin",
  "description": "Falsifiable research planning for AI agents: pressure-test claims, freeze evaluators, use AI-lab and medical evidence patterns, build proof ladders, and maintain proof ledgers.",
  "version": "1.3.0",
  "author": {
    "name": "Tony Blanco"
  },
  "homepage": "https://github.com/tonyblu331/research-proof",
  "repository": "https://github.com/tonyblu331/research-proof",
  "license": "MIT",
  "keywords": [
    "agent-skills",
    "claude-code",
    "research",
    "research-agent",
    "ai-research",
    "evaluation",
    "evals",
    "benchmarking",
    "proof",
    "proof-ledger",
    "falsification",
    "scientific-method",
    "medical-research",
    "evidence-certainty",
    "prompt-engineering",
    "autonomous-agents"
  ]
}
Changes

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.

  1. 2d ago First seen · 30 lines scan A 0566be1f807a

Subscribe to this mod's changes

research-proof-plugin is a plugin published in the GitHub repository tonyblu331/research-proof (45 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-30.

PlanningResearchTestingagent-workflowsai-researchbenchmarkingresearch-automationresearch-tool
Related

Other plugins, from other repositories

airas

Automated research with AIRAS: paper search, hypothesis generation, experiment execution on GitHub Actions/AIXS, figure rendering, and paper writing — bundles the AIRAS MCP server (uvx airas) and research-workflow skills.

airas-org/airas · not measured

airas

Automated ML research tools: the AIRAS MCP server plus research-workflow skills.

airas-org/airas · not measured

agent-lifecycle-kit

Plugin marketplace listing 1 plugin: agent-lifecycle-kit.

avksp/agent-lifecycle-kit · not measured

vukkt-plugins

Plugins by Vuk Topalovic — currently token-warden, a measurement and selection layer that makes Claude Code subagents measurably cheaper over time.

vukkt/token-warden · not measured

warranted

Make AI research agents accountable — give every conclusion a traceable argument graph.

yqi96/warranted · not measured

tmcp

Standalone TMCP skill-packet workflows, first-run checks, skill harvesting, adaptive workflow-pack recommendations, packet substance checks, and expert rubric remediation for Claude Code.

jakyeamos/tmcp · not measured