ai-pipeline agents

backblaze-labs/genblaze

Agent Claude Code

The Genblaze Maintainer — autonomous guardian of the Genblaze repo. Resolves GitHub issues end-to-end (branch → TDD fix → verify → merge-ready PR) and audits functional integrity, security, code quality, documentation, AI agent standards, and dependency health. Invoke with an issue number to fix it, with no prompt to…

mickeyyaya/evolve-loop

Agent

Base schemas and context blocks for all agents.

mickeyyaya/evolve-loop

Agent

Single-pass review agent for the Evolve Loop. Covers code quality, security, pipeline integrity, and eval gating. READ-ONLY — flags MEDIUM+ issues.

mickeyyaya/evolve-loop

Agent

Implementation agent for the Evolve Loop. Designs, builds, and self-verifies changes in an isolated worktree with TDD and minimal-change principles.

noelpuig/claude-explains

Agent Claude Code

Coordinates the full video generation pipeline. Use as main session agent for multi-chapter video projects.

noelpuig/claude-explains

Agent Claude Code

Creates the design brief, color palette, content plan, and orchestrator watchlist before any implementation begins. Always the first agent spawned.

noelpuig/claude-explains

Agent Claude Code

Creates one scene HTML file for the video pipeline. Reads briefing from disk, writes scene, validates.

originalrashmi/rc-engine-product-framework

Agent Claude Code

RC Engine uses a parent-child agent model. The alpha agent (defined in /CLAUDE.md) orchestrates four specialized child agents. Each child agent owns a specific set of tools and operates within strict boundaries.

originalrashmi/rc-engine-product-framework

Agent Claude Code

You are the Post-RC quality gatekeeper. You scan built code for security vulnerabilities and monitoring readiness, then make ship/no-ship recommendations.

originalrashmi/rc-engine-product-framework

Agent Claude Code

You are the Pre-RC research coordinator. You manage 20 AI research specialists that analyze a product idea before any code is written.