A "Token Firewall" for MCP - reduce AI token costs by 50-80% while securing your code from secret leaks.
This repository also configures its own agents. See what leanproxy-mcp tells them →
Command Claude CodeOpenCode
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
Command Claude CodeOpenCode
Strategic business analyst and requirements expert. Use when the user asks to talk to Mary or requests the business analyst.
Command Claude CodeOpenCode
System architect and technical design leader. Use when the user asks to talk to Winston or requests the architect.
Command Claude CodeOpenCode
Senior software engineer for story execution and code implementation. Use when the user asks to talk to Amelia or requests the developer agent.
Command Claude CodeOpenCode
Product manager for PRD creation and requirements discovery. Use when the user asks to talk to John or requests the product manager.
Command Claude CodeOpenCode
Technical documentation specialist and knowledge curator. Use when the user asks to talk to Paige or requests the tech writer.
Command Claude CodeOpenCode
UX designer and UI specialist. Use when the user asks to talk to Sally or requests the UX designer.
Command Claude CodeOpenCode
Produce the architecture: a lean spine of invariants that keeps everything built from it consistent, projected into whatever format the work needs. Use when the user says "create the architecture", "create technical architecture", "architecture spine", or "create a solution design".
Command Claude CodeOpenCode
Facilitate a brainstorming session using diverse creative techniques. Use when the user says 'help me brainstorm' or 'help me ideate'.
Command Claude CodeOpenCode
Validate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness".
Command Claude CodeOpenCode
LLM-assisted human-in-the-loop review. Make sense of a change, focus attention where it matters, test. Use when the user says "checkpoint", "human review", or "walk me through this change".
Command Claude CodeOpenCode
Review code changes adversarially using parallel review layers (Blind Hunter, Edge Case Hunter, Acceptance Auditor) with structured triage into actionable categories. Use when the user says "run code review" or "review this code".
Command Claude CodeOpenCode
Manage significant changes during sprint execution. Use when the user says "correct course" or "propose sprint change".
Command Claude CodeOpenCode
DEPRECATED — consolidated into bmad-architecture create intent - this skill will be removed in v7 in favor of bmad-architecture.
Command Claude CodeOpenCode
Break requirements into epics and user stories. Use when the user says "create the epics and stories list".
Command Claude CodeOpenCode
DEPRECATED — consolidated into bmad-prd create intent - this skill will be removed in v7 in favor of bmad-prd.
Command Claude CodeOpenCode
Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "create the next story" or "create story [story identifier]".
Command Claude CodeOpenCode
Authors and updates customization overrides for installed BMad skills. Use when the user says 'customize bmad', 'override a skill', 'change agent behavior', or 'customize a workflow'.
Command Claude CodeOpenCode
One iteration of an unattended development loop. Use when invoked by name.
Command Claude CodeOpenCode
Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan".
Command Claude CodeOpenCode
Document brownfield projects for AI context. Use when the user says "document this project" or "generate project docs".
Command Claude CodeOpenCode
Conduct domain and industry research. Use when the user says wants to do domain research for a topic or industry.
Command Claude CodeOpenCode
DEPRECATED — consolidated into bmad-prd update intent - this skill will be removed in v7 in favor of bmad-prd.
Command Claude CodeOpenCode
Clinical copy-editor that reviews text for communication issues. Use when user says review for prose or improve the prose.
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: