17 tagged harness-framework, measured the same way as everything else here.
Browse within: agent 12vibe-coding 11harness-engineering 6agents 5
walkinglabs/learn-harness-engineering
Skill Codex
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
Skill Claude CodeCodex
Fill a whole web form, post a comment or reply, or read a long thread in Safari or Chrome with the fewest Mac MCP browser calls.
Skill Claude CodeCodex
You have persistent, file-based memory at ./drive/ in your workdir. Everything you write here survives the run. Read it on every wake. Save deliberately, in small useful pieces, at the right scope.
Skill Claude CodeCodex needs its repo
A product-design workflow for planning screens, user interactions, and task flows. It requires key interaction details to be confirmed before producing a design, and creates static HTML files when HTML is needed.
duck-lint/coding-agent-harness
Skill Claude CodeCodex
Seed the current working directory/repo with the coding harness using a python script. Also offers explicit approval-gated installation of harness subagent TOMLs into /.codex/agents.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: