frankaging/lite-research-agents
Instructions file CodexOpenCode
Instructions for frankaging/lite-research-agents, covering codex cli — research agent boot contract, on startup, sandbox rule, invoking skills and no subagent spawning.
frankaging/lite-research-agents
Instructions file
Instructions for frankaging/lite-research-agents, covering claude code — research agent boot contract, on startup, sandbox rule, invoking skills and no external processes.
frankaging/lite-research-agents
Skill Claude CodeCodex
Search and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.
frankaging/lite-research-agents
Skill Claude CodeCodex
Core research principles that govern all project decisions. Load this skill for every research project. Every idea, method, and artifact must be evaluated against these principles before proceeding.
frankaging/lite-research-agents
Skill Claude CodeCodex
Defines how to save and load agent state as checkpoint files.
frankaging/lite-research-agents
Skill Claude CodeCodex
Mechanism for keeping an agent anchored to a caller-defined persona across sessions. Covers the biplate private memory system for drift detection and self-correction.
frankaging/lite-research-agents
Skill Claude CodeCodex
Defines the structure and requirements for a research proposal.
frankaging/lite-research-agents
Skill Claude CodeCodex
Probe system resources — CPU, RAM, disk, GPU/CUDA/MPS — and translate findings into experiment design recommendations. Run this at the start of any compute-intensive project.
frankaging/lite-research-agents
Skill Claude CodeCodex
Multi-agent research war room. Personas debate in sequential turns through two phases — ideation and proposal writing. Persona persistence and drift detection are enforced every turn via the persistent-persona skill.