Agent
Reviews code for "taste" — does it read well, match the codebase's idioms, feel clean? Uses CommandCode's taste-1 model. NOT a bug hunter; pair with the Codex reviewer.
9 tagged free tier, measured the same way as everything else here.
Browse within: agentic-systems 6claude-plugin 6
Agent
Reviews code for "taste" — does it read well, match the codebase's idioms, feel clean? Uses CommandCode's taste-1 model. NOT a bug hunter; pair with the Codex reviewer.
Agent
Mechanical refactors at scale — renames, signature changes, file splits, codemods. Fast, multi-file, model-agnostic. Best for "do this same change in 40 places".
Agent
Writes tests for existing code. Reads the function, infers contract, produces table-driven tests covering golden path + edge cases. Does not modify production code.
Agent
Researches and creates new Bricolage domains. When a user's goal doesn't match any existing domain, the discovery agent searches for free resources, scaffolds a new domain, populates its catalog, and creates starter patterns. Also updates existing domains with new resources.
Agent
Helps users set up agent infrastructure on their own provisioned free compute. Deploys OpenClaw, MiniClaw, or PicoClaw runtimes. Configures cron jobs, MCP server connections, and agent-to-agent communication channels.
Agent
Analyzes a user's goal and selects the best free resources from a domain's catalog to achieve it. Outputs a structured plan. Domain-agnostic — works with any domain by reading its resource catalog and patterns.