Stand up, assess, and maintain an agentic harness in an existing repo.
A meta-tool that generates project-specific agent teams and the skills they use, then assesses how effectively they are used. When a spec-driven development system or an issue tracker is present, the generated orchestrator coordinates with it — activating the spec workflow and resuming on hand-back, pulling ready work and writing status back. More
Skills 7 in the Claude listing
Harness doctor Check whether this machine has what a project's agentic harness needs — the plugins, skills, MCP servers, CLIs, and API-key variables named in its tools registry — and report each as ok, missing, disa Harness feedback Run a kaizen retrospective on an agentic-harness run and, with the user's consent, file tool-improvement feedback as a GitHub issue on the upstream agentic-harness repo. Harness review Assess an existing agentic harness — read-only. Harness setup Build, extend, and maintain a project's agentic harness — the agents, skills, and orchestrator under .claude/. Spec advisor Detect whether a software project lacks a spec-driven development system and, if so, advise which one fits (GitHub Spec Kit, OpenSpec, BMAD-METHOD, Agent OS, Taskmaster, AWS Kiro, ADR tooling) and del Tracker advisor Detect whether a software project lacks an issue tracker suited to agentic work and, if so, advise which one fits (Beads, Backlog.md, git-bug, git-issues, Beans, or GitHub Issues, Linear, Jira via the Visual advisor Choose and set up the visual tooling for a project's agentic harness — which review surface (lavish, visual-explainer, static files) and which asset generators (image APIs, diagram tools, design MCPs) 