A command-line tool for organizing the information an AI coding assistant uses while working on a project. It is built around evidence, tests, and written specifications.

It is intended for evidence-based development workflows, including test-driven development (writing tests before or alongside code), specification-driven work, and detecting when project information has drifted.

It helps reduce mistakes caused by missing, outdated, or conflicting project context. The available details do not explain exactly how its checks work.

mpga — Plugin by benrben

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 benrben/MPGA

agentmods

npx agentmods add plugins/benrben/mpga/mpga-plugin

Clone the repo

git clone --depth 1 https://github.com/benrben/MPGA

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

mpga 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 yesterday.

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.

mpga-plugin/.claude-plugin/plugin.json · 25 lines

What it actually says

{
  "name": "mpga",
  "version": "1.0.0",
  "description": "Make Project Great Again — evidence-backed context engineering for AI-assisted development",
  "author": {
    "name": "MPGA Contributors"
  },
  "repository": "https://github.com/mpga-dev/mpga",
  "license": "MIT",
  "keywords": [
    "context-engineering",
    "evidence",
    "tdd",
    "drift-detection",
    "spec-driven"
  ],
  "setup": {
    "script": "scripts/setup.sh",
    "description": "Builds the bundled MPGA CLI from source (pip install -e .)"
  },
  "bin": {
    "mpga": "bin/mpga.sh"
  }
}

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.

yesterday First seen · 25 lines scan A 053ff99dcac5

Subscribe to this mod's changes

mpga is a plugin published in the GitHub repository benrben/MPGA (5 stars, last pushed 4mo 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 2026-08-31.

Testing Writing and docs

mpga

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

nextjs

nextjs

claude-plugins-official

knowledge-work-plugins

ecc

ecc