Harnesses
3 entries in 6 categories. Entries marked draft have not been checked against their sources yet. Each harness is listed under its primary category.
Categories:
- Workflow methodologies
- Spec-driven toolkits
- Multi-agent orchestrators
- Autonomous loops
- Memory and context
- Skill collections
Workflow methodologies
An opinionated development process, from idea to merged code, packaged as skills, commands, and subagents.
- Compound Engineering (Every (Kieran Klaassen and Trevin Chow)) draft - Every's plugin for a six-step loop (brainstorm, plan, work, simplify, review, compound) that puts most of the effort into planning and review and writes each lesson to docs/solutions/, where later runs look it up.
- pstack (Lauren Tan (poteto), published in Cursor's plugin repository) draft - A Cursor plugin in which one command, /poteto-mode, routes each task to one of 23 playbooks that require reproducing problems first, verifying on the real surface, review by several models, and small stacked pull requests.
- Superpowers (Jesse Vincent (obra) and Prime Radiant) draft - A skills library that gives a coding agent a fixed process, from brainstorming and a written spec through test-first implementation, per-task review, and a branch-finish menu, loaded automatically at the start of every session.
Spec-driven toolkits
Turn requirements into a written spec and task list before any code is written.
No entries yet.
Multi-agent orchestrators
Run and coordinate several agents at once, usually in separate sessions or worktrees.
No entries yet.
Autonomous loops
Keep an agent working toward a goal over many iterations with little supervision.
No entries yet.
Memory and context
Give agents persistent memory or curated context across sessions.
No entries yet.
Skill collections
Libraries of independent skills, agents, or commands with no single prescribed process.
No entries yet.