Loop Engineering

Comet: agent skill harness for turning ideas into evaluated workflows

Agentic AI job discovery platform featuring Loop Engineering, multi-agent orchestration, resume intelligence, semantic fit scoring, autonomous monitoring, and real-time career recommendations.

Mobile AI Skills, Agents and workflow to help you build mobile apps and games faster. A collection of AI skills, agents, prompts, and workflows for Android, iOS, Flutter, React Native, Unity, and Unreal developers. Use these ready-made tools to write code faster, fix bugs, review code, improve performance, automate tasks, and ship faster with AI.

An autonomous product loop for Claude Code that improves a real product overnight: a value gate before any code, an independent validator after, a deterministic driver that knows when to stop, and a one-command installer. Hardened by live runs on an iOS app and its backend.

An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes. Turn task evidence into actionable team and organization insights.

A Codex-native loop-engineering environment for long-running, multi-agent implementation with built-in review.

Claude Code plugin for agentic loop-engineering: PRD design/import, tagged phase planning, and an autonomous TDD execution loop with deterministic escalation and disk-backed state.

The public home for FifthDev and Fabric: reliable agent context, local code intelligence, and governed workflows.

Harness-first agent research: a bounded act→verify loop runner with one-line adapters for 10 lean harnesses (Pi, Hermes, aider, Codex, Goose, Claude, Ollama…) + Crucible, a portable benchmark that scores the harness, not the model — gated Safety×Completion/Path/State Goodput, factorial harness×model×seed, cost & local-vs-cloud routing.

A fixed loop for building with Claude Code: a lead agent, three specialised sub-agents (builder, reviewer, control), a deterministic gate, and two human gates. Plain files only: skills, agents, slash commands, rules and a markdown vault. Prototype.

Autonomous closed-loop multi-agent software delivery pipeline for Salesforce development with JIRA, Slack, and GitHub integration.

Claude Code plugin that builds deterministic multi-agent dev pipelines — define the graph in YAML, scaffold agents into your repo, run with spec gates, feedback loops, and resume.

A zero-dependency workflow that keeps a codebase's decisions, work, and definition of done honest and enforced by a git hook and CI, not by anyone remembering to.

Interactive Loop Engineering workshop for learning safe agentic coding with GitHub Copilot CLI

Loop engineering for AI agents.

A best-practices template for AI-assisted development at scale. It turns your repository into institutional infrastructure where AI agents can work sustainably — converging around documentation as a stable attractor across sessions, long cycles, and multi-role collaboration

A Claude Code workflow template for controlled AI-assisted development with human decisions, verification, review, and telemetry.

Governed self-evolution host (jea): Cyber-Taoist evolution theory × Loop Engineering — OADA closed loops with goal self-correction, multi-subject daemon, verify gates & auditable receipts.

Claude Code-based loop engineering template adapts any kind of development projects

Loop engineering for software development. Turn any repository into a self-organizing AI engineering team — 8 specialists, contract-driven, evidence-gated, parallel feature voyages.