16 tagged harness framework, measured the same way as everything else here.
Browse within: harness-engineering 6agentic-workflow 5vibe-coding 5
walkinglabs/learn-harness-engineering
Skill Claude CodeCodex
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
The brain is one Postgres-backed store over your books, your relationships, and your memory. It has four retrieval tiers and one synthesis verb. You reach it through the brain. tools — and so can external AI tools, over MCP.
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
Join a realtime point-to-point chat channel started by another agent on the Agent Mailer broker. Invoke as /agentjoinchat.
Skill Claude CodeCodex
Start a realtime point-to-point chat channel with another agent over the Agent Mailer broker. Invoke as /agentstartchat . Creates a channel, prints a join token # for the human to relay to the other operator, then runs a turn-taking poll loop that auto-replies until the channel is closed or paused (maxturns / TTL).…
Skill Claude CodeCodex
Bootstrap a multi-agent team for the Agent Mailer Protocol via fully conversational setup. In claude code or codex chat, asks the user what agents they want, drafts systemprompts, confirms, then writes team.yaml and runs agent-mailer up-team to register agents and generate launcher scripts. Idempotent — re-running…
Skill Claude CodeCodex
Review code changes for bugs, regressions, missing tests, and unclear behavior.
Skill Claude CodeCodex
Explore a codebase wiki-first, then confirm with read-only code evidence and cited paths.
Skill Claude CodeCodex
Write wiki documents a newcomer can actually read — plain-language entry, then design-spec depth.
Skill Claude CodeCodex
The Octowiz doctor — diagnose, monitor, and fix the full octowiz + AELLI integration. Use whenever octowiz or AELLI isn't behaving correctly, a hook isn't firing, an advisory isn't returning, or you want a real-time activity feed. Also guides first-time setup, configuration from scratch, and upgrading from older…
Skill Claude CodeCodex
Setup orchestrator for the Octowiz Bridge. Re-runs the live environment check, builds a gap list, and runs only the phases needed: plugins, memory, repo, verify. Invoked automatically by octowiz:octowiz when hard gaps are detected.
Skill Claude CodeCodex
Octowiz AI coding workflow coordinator. Reads IntegraHub memory doctrine at runtime, detects where you are in the development lifecycle, and routes to the right skill combination from superpowers + mattpocock-skills. Use this skill at the START of any development work — whether you have a fresh idea, an existing plan…
duck-lint/coding-agent-harness
Skill Claude CodeCodex
A decision matrix is a structured framework for evaluating and comparing different options or courses of action based on specific criteria. It helps in making informed decisions by systematically assessing the pros and cons of each option against defined factors.
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.