aivo0

aivo0/rlm-plugin

Plugin Claude Code

Recursive LLM agent — processes large contexts through iterative Python code generation, chunking, and sub-queries via claude -p.

aivo0/rlm-plugin

Agent

Process large contexts that exceed the context window by writing Python scripts that chunk, sub-query, and synthesize results iteratively. Use this agent when asked to analyze, summarize, or transform large files or datasets.

aivo0/rlm-plugin

Command

Process large contexts using the RLM (Recursive LLM) agent — chunking, sub-querying, and synthesizing results iteratively.

aivo0/research-team

Plugin Claude Code

Autonomous research team that finds, implements, verifies, and documents improvements in one cycle per run.

aivo0/research-team

Agent

Use this agent to verify that an implemented code improvement actually works. It designs and runs ablation studies, benchmarks, and empirical tests to produce quantitative evidence of improvement or regression. It does NOT modify the implementation — it only observes and measures. Context: The implementer has made…

aivo0/research-team

Agent

Use this agent to implement a specific, well-defined code improvement. It reads an improvement specification from a scout report, creates an implementation plan, makes minimal targeted code changes, runs tests, and captures the diff. Context: The research coordinator has a scout report with a top-ranked improvement.…

aivo0/research-team

Agent

Use this agent when searching for state-of-the-art techniques, relevant research, and evidence-backed improvements applicable to a codebase. This agent specializes in scientific literature review, adjacent-field cross-pollination, and grounding improvement suggestions in published evidence. Context: The research…

aivo0/research-team

Agent

Use this agent to review a completed research cycle, make an evidence-based accept/reject decision, update documentation, maintain the improvement backlog, and suggest the direction for future cycles. Context: All phases of a research cycle are complete and need final review. user: "Review cycle 3: scout report…

aivo0/research-team

Command

Resume a failed or interrupted research cycle.

aivo0/research-team

Command

Run one autonomous research-implement-verify-review cycle.

aivo0/research-team

Command

Show current research team state, progress, and backlog.