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.
git clone --depth 1 https://github.com/keepwhatworks/trinityWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/keepwhatworks/trinity/trinity-local)<a href="https://agentmods.dev/plugins/keepwhatworks/trinity/trinity-local"><img src="https://agentmods.dev/badge/plugins/keepwhatworks/trinity/trinity-local/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/keepwhatworks/trinity/trinity-local"><img src="https://agentmods.dev/badge/plugins/keepwhatworks/trinity/trinity-local.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
trinity-local 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 17d 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.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "trinity-local",
"displayName": "Trinity Local",
"version": "1.7.389",
"description": "Ask all three. Keep what works. Put plans in front of Claude, Codex and Gemini before you commit, and check changes with your own tests before you call them done. Local-first: your transcripts stay on your machine, on the subscriptions you already pay for.",
"author": {
"name": "Vishi Gondi",
"url": "https://keepwhatworks.com"
},
"homepage": "https://keepwhatworks.com",
"repository": "https://github.com/keepwhatworks/trinity",
"license": "MIT",
"keywords": [
"council",
"review",
"verify",
"multi-model",
"cross-provider",
"local-first",
"claude",
"codex",
"gemini"
],
"commands": [
"./commands/"
],
"mcpServers": "./.mcp.json"
}
What it installs
The manifest is a name and a version. 1 skill, 3 commands, 1 agent, 1 MCP server travel with it, and installing the plugin installs all of them — 255 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 17d ago Changed · +4 lines ab9e55e8afbe
- 1mo ago First seen · 26 lines scan A 64c6e7128c92
trinity-local is a plugin published in the GitHub repository keepwhatworks/trinity (1 stars, last pushed 5d 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.
Other plugins, from other repositories
prompt-engineering-skills
A prompt-engineering toolkit that turns ideas into executable prompts. It includes a prompt-generation command, model-specific guides for Claude, GPT, Gemini, and image models, and a prompt kit.
notify-me
Calls you back when an agent needs you. The moment an agent gets blocked waiting on your decision, notify-me pushes a notification to your phone (via ntfy) and/or plays a sound on your computer — so you can step away and still know when you're needed. Works with any agent that supports plugin hooks. No account, no…
skillctx
Make your agent skills portable by extracting hardcoded values into a central config and embedding resolver scripts.
gemini
Gemini via Antigravity CLI for Claude Code — ask, review, adversarial-review, implement.
mosaic-bridge
Mosaic Bridge — Unity MCP assistant agents for scene building, shader creation, and session continuity.
video-intel
YouTube video intelligence via Gemini: channel scanning, rich multimodal transcripts with on-screen content, concept taxonomy, hybrid search, and Bosnian/Croatian/Serbian subtitle translation. Three skills: video-intel (ingest/curate, runs in the plugin repo), video-intel-search (read-only, globally installable)…