sgharlow

AI Control Framework — AI skill for Claude Code

AI community

Verification gates for AI-assisted code: deployment-readiness scoring, specs, checklists.

How to install AI Control Framework

This entry records only its repository, not the path inside it, so there is no exact command to give. Open sgharlow/ai-control-framework and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What AI Control Framework does

Verification gates for AI-assisted code: deployment-readiness scoring, specs, checklists. npx ai-control-framework

Alternatives in AI

Codeburn — Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Code 9.7k ★
AI Readiness — AI 就绪度评估 — 单票 AI 暴露/卡位评级 + 三道 gate + Top 杠杆点 6.6k ★
ML Deployment Pack — Machine learning model deployment skills 1.6k ★

README

AI Control Framework

[![Workshown](https://img.shields.io/badge/Workshown-member-0b7285)](https://sgharlow.github.io/ai-control-framework/) **Part of [Workshown](https://sgharlow.github.io/ai-control-framework/) — show your work.** [ai-control-framework](https://github.com/sgharlow/ai-control-framework) (the how) · [orchestra-lite](https://github.com/sgharlow/orchestra-lite) (the scale) · [ai-pr-bot](https://github.com/sgharlow/ai-pr-bot) (the enforcement) · [skillcrossroads](https://github.com/sgharlow/skillcrossroads) (the grade) · [recipes](https://github.com/sgharlow/claude-code-recipes) (the front door) · [case study](https://github.com/sgharlow/distraction)

**Stop wasting time on non-deployable AI-generated code. Ship with confidence.**

[![Version](https://img.shields.io/badge/version-2.1.0-blue)]() [![License](https://img.shields.io/badge/license-MIT-purple)]() [![CI](https://github.com/sgharlow/ai-control-framework/actions/workflows/ci.yml/badge.svg)](https://github.com/sgharlow/ai-control-framework/actions/workflows/ci.yml)

**What CI actually verifies** (this framework's own rule — no claim without a check): the 28-check validation suite, the MCP server build on Node 20/22, and the dashboard's 14 vitest tests on Node 20/22. An earlier "136/136 tests" badge here referenced a runner that no longer exists in the repo and has been retired.

**Dogfood score:** the framework run against its own repo scores **DRS 27/100** (2026-07-18, `ai-framework/reference/bash/drs-calculate.sh`) against its own ship threshold of 85. Published as-is: most DRS components measure live-session artifacts (frozen contracts, fresh evidence, integration proofs) that a framework *repo* does not carry — the score is honest, and low, and that is the point of the tool.