HanLi-Chainsea/han-agents
Skill Claude CodeCodex
Multi-agent task system for complex tasks. Three-layer architecture (Skill + Code Graph + Memory), task lifecycle with validation, semantic search, drift detection. Use when: user requests PFC agent, complex multi-step tasks, multi-agent coordination, or mentions han.
HanLi-Chainsea/han-agents
Agent
A red-team review agent that examines plans for risks, logical gaps, and security problems. Red-team review means deliberately trying to find ways a plan could fail.
HanLi-Chainsea/han-agents
Agent
A checker for differences between a single source of truth and the code. It produces suggestions for correcting those differences.
HanLi-Chainsea/han-agents
Agent
An agent for completing one small, self-contained task and then stopping.
HanLi-Chainsea/han-agents
Agent
A knowledge-memory agent for saving learned information, finding it later, and maintaining working notes. The description provides no further detail about how that memory is stored or searched.
HanLi-Chainsea/han-agents
Agent
An agent named pfc from the HanLi-Chainsea/han-agents project. Its description identifies it as a task coordinator and mentions databases, responsibilities, execution modes, and workflows.
HanLi-Chainsea/han-agents
Agent
A research and information-gathering agent that searches documents, reads code, and collects relevant details.