Agent Claude Code
Internal agent for reviewing staged code changes against CAS rules. Checks for rule compliance, patterns, and quality. Spawned before commits or on demand.
Agent Claude Code
Internal agent for reviewing staged code changes against CAS rules. Checks for rule compliance, patterns, and quality. Spawned before commits or on demand.
Agent Claude Code
Internal agent for finding and consolidating duplicate or near-duplicate memories, rules, and learnings. Spawned periodically for cleanup.
Agent Claude Code
Internal agent for reviewing learnings and promoting them to rules or skills. Spawned automatically when unreviewed learnings exceed threshold. Do not invoke directly.
Agent Claude Code
Internal agent for reviewing draft rules. Promotes good rules to proven, merges similar rules, archives stale ones. Spawned when draft rules exceed threshold.
Agent Claude Code
Internal agent for generating session summaries at stop. Creates a concise summary of work done, decisions made, and learnings captured. Spawned by Stop hook.
Agent Claude Code
Internal agent for verifying task completion. Spawned automatically on task close. Do not invoke directly.
Hook Claude Code
Runs when the agent sends a notification for permission_prompt, idle_prompt and auth_success tool calls, running cas hook Notification. From codingagentsystem/cas.
Hook Claude Code
Runs when the agent asks permission for an action, running cas hook PermissionRequest. From codingagentsystem/cas.
Hook Claude Code
Runs after a tool call finishes for Write, Edit and Bash tool calls, running cas hook PostToolUse. From codingagentsystem/cas.
Hook Claude Code
Runs before the context is compacted, running cas hook PreCompact. From codingagentsystem/cas.
Hook Claude Code
Runs before the agent uses a tool for Read, Glob, Grep, Write, Edit, Bash, WebFetch, WebSearch, Task and SendMessage tool calls, running cas hook PreToolUse. From codingagentsystem/cas.
Hook Claude Code
Runs when a session ends, running cas hook SessionEnd. From codingagentsystem/cas.
Hook Claude Code
Runs when a session starts, running cas hook SessionStart (2 commands). From codingagentsystem/cas.
Hook Claude Code
Runs when the agent finishes a response, running cas hook Stop. From codingagentsystem/cas.
Hook Claude Code
Runs when a subagent starts for task-verifier tool calls, running cas hook SubagentStart. From codingagentsystem/cas.
Hook Claude Code
Runs when a subagent finishes, running cas hook SubagentStop. From codingagentsystem/cas.
Hook Claude Code
Runs when you submit a prompt, before the agent sees it, running cas hook UserPromptSubmit. From codingagentsystem/cas.
Settings file Claude Code
Agent settings declaring 11 hook events (Notification, PermissionRequest, PostToolUse, PreCompact) and 4 allowed tools.
Skill Claude CodeCodex
How to store and retrieve persistent memories using CAS. Use for facts, preferences, learnings, and context that should persist across sessions. Trigger when discovering patterns, fixing bugs, resolving config issues, or learning how unfamiliar code works.
Skill Claude CodeCodex
Search across CAS content (memories, tasks, rules, skills, code). Use when needing to find information, understand codebase, or locate specific patterns. Supports hybrid BM25+semantic search, code symbol search, grep, context, and entity operations.
Skill Claude CodeCodex
Quick startup checklist for factory supervisors. Use at the beginning of a factory session to load context, check EPICs, and confirm worker availability.
Skill Claude CodeCodex
Factory supervisor guide for multi-agent EPIC orchestration. Use when acting as supervisor to plan EPICs, spawn and coordinate workers, assign tasks, monitor progress, and merge completed work. Covers worker count strategy, conflict-free task coordination, epic branch workflow, and completion verification.
Skill Claude CodeCodex
How to track work using CAS tasks instead of built-in TodoWrite. Use for persistent task tracking with priorities, dependencies, structured notes, and cross-session continuity.
Skill Claude CodeCodex
Factory worker guide for task execution in CAS multi-agent sessions. Use when acting as a worker to execute assigned tasks, report progress, handle blockers, and communicate with the supervisor.