
Audits GitHub Actions workflows that run AI coding agents for prompt injection risks
- Open source
- 8.2K GitHub stars
- AI models and LLM tooling


Audits GitHub Actions workflows that run AI coding agents for prompt injection risks

Generates prompts that make an agent document end-to-end workflows as implementation

Runs an AI-readiness scan on a repo and builds a static HTML scoring dashboard

Runs a full quality audit on a codebase, with generated tests, code review and spec checks

Designs AI agent architectures from requirements or audits existing agents for flaws

Guides a codebase through pre-audit prep: goals, static analysis, coverage and docs

Guides reviewers through pull requests to awesome-copilot for fit, value and provenance

Guides an agent through a security-focused review of PR, commit or diff changes

Reviews frontend UI code against design systems and builds distinctive interfaces

Guides an agent through drafting, testing and tuning new agent skills with measured evals

Audits a site's load and interaction speed, Core Web Vitals and Lighthouse scores

Audits and fixes how ready a site is for AI browsing agents, from llms.txt to WebMCP
The closest alternatives to Diagnose are Agentic actions auditor, Project workflow analysis blueprint generator, Acreadiness assess, Quality playbook and Agent architecture.
Yes. Agentic actions auditor, Project workflow analysis blueprint generator, Acreadiness assess have a free or open-source option.