Plugin marketplace

agent-harness

A Claude Code harness by Jooeon Kim (K021) — skills and agents to customize how the coding agent works. Ships two sibling skills that let a fresh session recover what you're doing and what files exist, plus a model-routing agent plugin that sends each delegated sub-agent task to the model tier it was measured to need.

1 · K021/agent-harness3 pluginsMITupdated 2 months ago

Add this marketplace

Then install any plugin below by name — each page has its exact command.

Route sub-agent (leaf) tasks to the right model by task type — measured twice on a real app build. Ships nine leaf-* agents (closed/executor work → low tier; open problems, discovery and the pre-merge gate → mid tier) that auto-delegate by description, plus an /apply command that adds the routing gate to your CLAUDE.md. Stops every delegation from silently burning your priciest tier — after the second pass no agent pins a top-tier model outright; a one-shot emergent implementation is the one place that tier is a measured win, and diagnose + repair keeps it too as an untested hedge for the hardest cases.

1 command · 9 agents

1

Gives your AI coding agent a memory of the work — a self-maintaining context index (project-context.json) that survives session resets and context-window compaction, so the agent recovers what it's building, where it is, and the next step instead of re-deriving it.

1 skill · hooks

1

Gives your AI coding agent a map of the files — a hot index of what files exist and what each does (project-structure.json + append-only history), recovered in a single read so a new session stops re-discovering the codebase by grep. Sibling to project-context.

1 skill · hooks

1

README badge

Shows how many plugins this repo ships, and links here.

claude & codex plugins3 plugins