Skill Claude CodeCodex
Confidence: high Domain: work-monitoring Last validated: 2026-03-24.
Drag-and-drop Kanban board that delegates coding tasks to AI agents — GitHub Copilot, Claude Code, OpenAI Codex, and OpenCode — with real-time streaming, task groups, and git worktree isolation.
This repository also configures its own agents. See what ai-agent-board tells them →
Skill Claude CodeCodex
Confidence: high Domain: work-monitoring Last validated: 2026-03-24.
Skill Claude CodeCodex
Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.
Skill Claude CodeCodex
Skill "release-process" from DanWahlin/ai-agent-board, covering release process, scope, confidence: high, context and rules (non-negotiable).
Skill Claude CodeCodex
Team-wide charter and history optimization through skill extraction.
Skill Claude CodeCodex
Ensure retrospectives happen on schedule and that their action items are tracked in GitHub Issues — not markdown checklists.
Skill Claude CodeCodex
Three-tier agent memory model (hot/cold/wiki) for 20-55% context reduction per spawn.
Skill Claude CodeCodex
Semver versioning rules for Squad SDK and CLI — prevents prerelease version incidents.
Skill Claude CodeCodex
Cross-platform path handling and command patterns.
Skill Claude CodeCodex
Use when Dan explicitly asks Claude, Codex, Copilot, Grok, Hermes, OpenCode, or OpenClaw to perform coding work. Route it through the shared AI Agent Board instead of launching the coding agent directly.
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: