Install project agent harnesses with rsc-harness
Let an agent run rsc-harness onboarding to plan and install project-specific memory, skills, guardrails, hooks, and workflow lanes only after human approval.
npx skills add agentskillexchange/skills --skill install-project-agent-harnesses-with-rsc-harness
npx @ericrisco/rsc@latest onboard. Review the questions and generated plan. Only rerun with --accept-plan after the user approves the exact printed plan.Use rsc-harness when a project needs a proportional agent harness instead of ad hoc skills, rules, hooks, and memory files. The operator asks an agent to run the onboarding flow, answer the project questions, review the generated plan, and approve the exact plan before anything is written. The scope boundary is project harness installation and maintenance for agent workflows; it is not a general framework, a skill catalog entry, or permission to rewrite a repo without review.
What this skill actually does
Inputs and prerequisites: Node.js/npm, a target project root, and one or more supported assistants such as Claude Code, Codex, Gemini, OpenCode, Cursor, Copilot, or DeepSeek Harness..
Setup notes: From the project root being equipped, run npx @ericrisco/rsc@latest onboard . Review the questions and generated plan. Only rerun with –accept-plan after the user approves the exact printed plan.
Source and verification boundary: use https://ericrisco.github.io/rsc-harness/ as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.