aot-evals

by Mahal Systems · ★ 6 · updated yesterday

Part of AOT, the Agent Optimization Toolkit, a Mahal Systems offering. Design, build, measure and iterate the evals for a production agent: a repository contract (evals/), skills that walk commands C0-C18 with exit gates, a stdlib CLI that runs the agent k times and records every attempt, and a fixed report.json schema that Claude renders into a local HTML diagnostic.

install aot-evals

Install

git clone https://github.com/Mahalanobis-Systems/aot-evals

claude --plugin-dir ./aot-evals

Then run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.

View source on GitHub

What it hooks into

From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.

Events: ui.render
API calls: $.ui.resolve
Draws: ToolResultToolGroup
Reach: level 0 of 3 draws

Origin

How it got here: Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of 18 Oct 2026).
Repository: github.com/Mahalanobis-Systems/aot-evals
Path in repo: repository root
Source commit: cf38f94 the exact code the scan read
Author: Mahal Systems @Mahalanobis-Systems
License: Apache-2.0
First published: 8 Oct 2026
Last pushed: 17 Oct 2026
First listed here: 19 Oct 2026

Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.