Skill Claude CodeCodex
Comprehensive security review checklist covering input validation, authentication, secrets management, and vulnerability patterns.
EVOKORE-MCP — a multi-server Model Context Protocol aggregator with skill discovery, HITL approval, RBAC, session continuity, and an opinionated orchestration framework.
This repository also configures its own agents. See what EVOKORE-MCP-PUBLIC tells them →
Skill Claude CodeCodex
Comprehensive security review checklist covering input validation, authentication, secrets management, and vulnerability patterns.
Skill Claude CodeCodex
Wrap up the current coding session by creating PRs, updating the session log, preparing the next session md, and updating the claude md with learnings.
Skill Claude CodeCodex needs its repo
Core concepts for goal-driven agents - architecture, node types (eventloop, function), tool discovery, and workflow overview. Use when starting agent development or need to understand agent fundamentals.
Skill Claude CodeCodex
Set up and install credentials for an agent. Detects missing credentials from agent config, collects them from the user, and stores them securely in the local encrypted store at /.hive/credentials.
Skill Claude CodeCodex
Best practices, patterns, and examples for building goal-driven agents. Includes client-facing interaction, feedback edges, judge patterns, fan-out/fan-in, context management, and anti-patterns.
Skill Claude CodeCodex
Iterative agent testing with session recovery. Execute, analyze, fix, resume from checkpoints. Use when testing an agent, debugging test failures, or verifying fixes without re-running from scratch.
Skill Claude CodeCodex
Complete workflow for building, implementing, and testing goal-driven agents. Orchestrates hive- skills. Use when starting a new agent project, unsure which skill to use, or need end-to-end guidance.
Skill Claude CodeCodex
Specialized skill for triage issue skill workflows.
Skill Claude CodeCodex
Core orchestration framework for model-agnostic multi-agent workflows with handoff protocol, policy governance, and configuration schemas.
Skill Claude CodeCodex
Agile Engineering Process (Align-Execute-Prove) methodology with phase planning, test matrices, and evaluation harnesses.
Skill Claude CodeCodex
Reference agent definitions with capability taxonomy for multi-agent orchestration.
Skill Claude CodeCodex
Quick-reference coding standards and backend patterns for consistent development.
Skill Claude CodeCodex
Registry and index of all orchestration command skills.
Skill Claude CodeCodex
Use when you need to spawn a specialist sub-agent to handle a specific task domain without polluting the main session context.
Skill Claude CodeCodex
Use when you need to check the current session's context usage and get recommendations for compaction or continuation.
Skill Claude CodeCodex
Use when you need to check the status of all running agents, workers, and claims in the current fleet.
Skill Claude CodeCodex
Use when ending a session and preparing for the next session — creates checkpoint, updates next-session.md, and ensures all PRs are tracked.
Skill Claude CodeCodex
Diagnose and fix build or test failures with minimal targeted changes.
Skill Claude CodeCodex
Synchronize documentation with code changes.
Skill Claude CodeCodex
Generate and run end-to-end tests for critical flows.
Skill Claude CodeCodex
Generate a session wrap summary documenting state, decisions, and recommended next steps.
Skill Claude CodeCodex
Invoke a Panel of Experts review on any artifact — code, architecture, plans, repos, or documentation.
Skill Claude CodeCodex
Create an approval-gated implementation plan with phased tasks and acceptance criteria.
Skill Claude CodeCodex
Dead code cleanup and refactoring without behavior changes.
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: