Skill Claude CodeCodex
Audits a WP brief for drift against current code — extracts claims, verifies each, emits PROCEED/STOP verdict. Use when starting a new WP, before consuming a spec as binding, or when a doc references paths/lines/functions.
Skill Claude CodeCodex
Template for structured sub-agent output including YAML log format, task completion reports (WHY/WHAT/TRADE-OFFS/RISKS), and summary constraints. Use when defining how sub-agents should report results.
Skill Claude CodeCodex
Template for structured sub-agent invocation using 4-part prompting (GOAL/CONSTRAINTS/CONTEXT/OUTPUT) and F# pipeline notation. Use when orchestrating sub-agents or designing multi-agent workflows.
Skill Claude CodeCodex
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
Skill Claude CodeCodex
Prompt template for test classification stage in Test Audit pipeline.
Skill Claude CodeCodex
Guidelines for creating unbiased test fixtures that integrate with project infrastructure. Use when creating fixtures for manual testing, setting up E2E test scenarios, or building code samples with deliberate issues for LLM review. Ensures fixtures work with hook automation and pass Phase 1 checks.
Plugin Claude Code
Context Layered Engineering for Agentic Resources - Persistent memory and intelligent context management for Claude Code sessions.
Agent
Architect sub-agent for plan-management Track B. Reads requirements and designs phase/workpackage decomposition with dependencies, confidence levels, and milestone checkpoints.
Agent
Detail Engineer sub-agent for plan-management Track B. Reads architect output and enriches each workpackage with acceptance criteria, deliverables, verification steps, and notes.
Agent
Requirements analyst sub-agent for plan-management Track B. Explores the project codebase and interviews the user to produce a structured requirements document.
Hook
Runs when a session starts, executing session-start.sh. From QBall-Inc/clear.
Hook
Runs before the context is compacted, executing session-precompact.sh. From QBall-Inc/clear.
Hook
Runs when you submit a prompt, before the agent sees it, executing user-prompt.sh. From QBall-Inc/clear.
Hook
Runs before the agent uses a tool for Read, Write, Edit, Glob, Grep and Bash tool calls, executing pre-tool.sh. From QBall-Inc/clear.
Hook
Runs after a tool call finishes for Write and Edit tool calls, executing post-tool.sh. From QBall-Inc/clear.
Hook
Runs when the agent finishes a response, executing session-stop.sh. From QBall-Inc/clear.
Hook
Runs when a session ends, executing session-end.sh. From QBall-Inc/clear.
Skill Claude CodeCodex
Run diagnostics on CLEAR state and optionally repair issues. Use when CLEAR state seems inconsistent or after manual edits to .clear/ files.
Skill Claude CodeCodex
Generate a session handoff document. Use when ending a session, reaching token thresholds, or previewing handoff contents.
Skill Claude CodeCodex
Interactive guide for CLEAR Framework. Helps discover commands and construct syntax through conversation.
Skill Claude CodeCodex
Provides help and guidance for CLEAR Framework commands. Use when the user needs a reference, command syntax, or a guided walkthrough of CLEAR features.
Skill Claude CodeCodex
Initialize the CLEAR framework in the current project. Use when a user wants to set up CLEAR for the first time, reinitialize an existing project (destructive), or refresh meta files (CLAUDE.md + rules.md) from the latest CLEAR templates (non-destructive).
Skill Claude CodeCodex
Manage the CLEAR knowledge base — search, view, capture, index, link, deprecate, and supersede entries. Use when the user asks about knowledge base entries, wants to capture a decision or lesson, search for patterns, or manage entry lifecycle.
Skill Claude CodeCodex
Manage and view the development plan — status, progress, blockers, phases, and next steps. Use when the user asks about plan status, needs next-step recommendations, wants to create or modify the plan, or asks about phases and milestones.