trinity

A local system that asks Claude, Codex, and Gemini for answers, then has a separate reviewer combine them into one result.

In plain words
What is it for?
Use it to request a council of model opinions, ask one question across providers, apply an optional personal preference lens, or route a task to a selected model.
Why use it?
Comparing several AI providers can expose disagreements and give you a basis for keeping the most useful answer.

Plugin for Claude Code

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 keepwhatworks/trinity
agentmods
npx agentmods add plugins/keepwhatworks/trinity/marketplace
Clone the repo
git clone --depth 1 https://github.com/keepwhatworks/trinity

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

trinity 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.

.claude-plugin/marketplace.json · 32 lines

What it actually says

{
  "$schema": "https://json.schemastore.org/claude-code-marketplace.json",
  "name": "trinity",
  "owner": {
    "name": "Vishi Gondi",
    "url": "https://keepwhatworks.com"
  },
  "description": "Trinity Local — ask all three, keep what works. Local-first cross-provider councils across Claude, Codex, and Gemini: a chairman synthesizes the verdict, an opt-in taste lens personalizes it, smart routing picks the winner.",
  "version": "1.0.0",
  "metadata": {
    "pluginRoot": "./plugins"
  },
  "plugins": [
    {
      "name": "trinity-local",
      "source": "./plugins/trinity-local",
      "displayName": "Trinity Local",
      "description": "Cross-provider councils, a taste lens, and smart routing — local-first. Registers the Trinity MCP server and adds /trinity-local:council, :ask, and :lens.",
      "version": "1.7.389",
      "author": {
        "name": "Vishi Gondi",
        "url": "https://keepwhatworks.com"
      },
      "homepage": "https://keepwhatworks.com",
      "repository": "https://github.com/keepwhatworks/trinity",
      "license": "MIT",
      "keywords": ["memory", "council", "multi-model", "routing", "cross-provider", "local-first"],
      "category": "productivity"
    }
  ]
}
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. yesterday First seen · 32 lines scan A c69748ac787b

Subscribe to this mod's changes

trinity is a plugin published in the GitHub repository keepwhatworks/trinity (1 stars, last pushed yesterday), 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.