Harnesses
9 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.
- gstack (Garry Tan (garrytan)) draft - Garry Tan's set of 55 skills, written for Claude Code, that runs a sprint through role-based steps, from product questioning and plan reviews to specialist code review, QA in a real browser, and a /ship command that ends with a pull request.
- 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.
- BMAD Method (Brian Madison (BMad Code, LLC)) draft - An agile method whose skills take an idea through briefs, a PRD, and a spec into a ticket tree of epics and stories, then build each story from an approved written plan checked by parallel reviewer subagents, with five named agent personas as guides.
- OpenSpec (Fission AI (lead maintainer Tabish Bidiwale, TabishB)) draft - A CLI plus generated skills and slash commands for 39 coding agents that has the agent write a proposal, requirement changes, a design, and a task checklist for each change before coding, then folds the requirement changes into specs kept in the repository when the change is archived.
- Spec Kit (GitHub (lead maintainer Manfred Riem, mnriem)) draft - GitHub's spec-driven development toolkit. A Python CLI installs ten commands, page templates, and scripts into a project for one of 40 coding agents; the commands turn a feature description into a spec, a plan, and a task list, then implement the tasks and check the code against those documents.
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.
- Ralph Loop (Anthropic (first written by Daisy Hollman); technique by Geoffrey Huntley) draft - Anthropic's Claude Code plugin for Geoffrey Huntley's Ralph Wiggum technique, in which a Stop hook feeds the same prompt back to the agent each time it tries to finish, until it prints an agreed completion phrase or reaches an iteration limit.
Memory and context
Give agents persistent memory or curated context across sessions.
- Agent OS (Brian Casel (Builder Methods)) draft - Five slash commands that write your codebase's conventions into short standards files, load the relevant ones into a conversation or plan on request, and save each plan-mode spec to the repository.
Skill collections
Libraries of independent skills, agents, or commands with no single prescribed process.
No entries yet.