advance
01Skill Claude CodeCodex
Claim and work on beads safely with proper coordination. Use when starting work, finishing work, or finding the next task. Covers the full bead lifecycle: discover → verify → claim → work → close.
Opinionated AI agent dev stack with tools, guides, templates, and workflows to take you from good to great.
Skill Claude CodeCodex
Claim and work on beads safely with proper coordination. Use when starting work, finishing work, or finding the next task. Covers the full bead lifecycle: discover → verify → claim → work → close.
Skill Claude CodeCodex
Multi-agent coordination with Agent Mail MCP. Use when registering agents, reserving files, sending messages, coordinating with other agents, or when the user mentions "agent mail", "coordination", "file reservation", or "multi-agent".
Skill Claude CodeCodex
Task tracking with the bd (Beads) CLI. Use when creating tasks, claiming work, closing beads, managing dependencies, or when the user mentions "beads", "bd", or "tasks".
Skill Claude CodeCodex
Graph analysis with bv (Beads Viewer). Use when analyzing the task graph, finding blockers, getting recommendations, checking critical path, or when the user mentions "bv", "graph", "dependencies", or "what should I work on".
Skill Claude CodeCodex
Run an evidence-seeking calibration roundtable to realign the plan with the North Star. Use when pausing between phases, when agents disagree, when reviewing work, when the user mentions "calibrate" or "realign", or when making decisions that affect the plan.
Skill Claude CodeCodex
Decompose a phase plan into atomic beads and sub-beads. Use when breaking down a phase into tasks, when the user mentions "decompose" or "break down", when creating beads from a plan, or when structuring work for parallel execution.
Skill Claude CodeCodex
Parallel codebase search with Warp-Grep MCP. Use for codebase discovery, understanding how things work, data flow analysis, or when the user asks "how does X work" about the codebase.
Skill Claude CodeCodex
Verify external libraries, APIs, and frameworks against current documentation. Use when implementing external dependencies, when unsure if a pattern is current, when the user mentions "ground", "verify docs", "exa", or "current API".
Skill Claude CodeCodex
New agent startup checklist for Agent Mail and Beads. Use when starting a new agent session, when the user says "prime" or "startup", or when beginning work on a multi-agent project.
Skill Claude CodeCodex
Retrieve context from past sessions before implementing. Use for learned patterns, past solutions, anti-patterns, session history, or when the user mentions "recall", "memory", "history", "cass", "cm", or "what do we know about".
Skill Claude CodeCodex
Release readiness checklist for shipping. Use after execution completes, when the user says "release" or "ship", or before deploying to production.
Skill Claude CodeCodex
Resolve disagreements between agents or approaches using test-based adjudication. Use when agents disagree, when multiple valid approaches exist, when the user asks "which approach", or when making architectural decisions with tradeoffs.
Skill Claude CodeCodex
Security scanning with UBS (Ultimate Bug Scanner). Use before commits, when scanning for bugs, when the user mentions "ubs", "bugs", "scan", "verify", or "security".
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: