mmornati/leanproxy-mcp

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 →

5Stars on the repository
97Mods indexed here, across every type
9d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Structural editor that proposes cuts, reorganization, and simplification while preserving comprehension. Use when user requests structural review or editorial review of structure.

not rated 5 9d ago A 35 tokens copy · 100% MIT

bmad-forge-idea

26

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Pressure-test an idea through persona-driven interrogation until it hardens, proves out, or dies cheaply. Use when the user says 'forge an idea', 'pressure-test this idea', 'stress-test my thinking', or 'harden this idea'.

not rated 5 9d ago A 56 tokens copy · 91% MIT

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Create project-context.md with AI rules. Use when the user says "generate project context" or "create project context".

not rated 5 9d ago A 31 tokens copy · 83% MIT

bmad-help

28

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Analyzes current state and user query to answer BMad questions or recommend the next skill(s) to use. Use when user asks for help, bmad help, what to do next, or what to start with in BMad.

not rated 5 9d ago A 51 tokens copy · 91% MIT

bmad-index-docs

29

mmornati/leanproxy-mcp

Skill Claude CodeCodex needs its repo

Generates or updates an index.md to reference all docs in the folder. Use if user requests to create or update an index of all files in a specific folder.

not rated 5 9d ago A 38 tokens copy · 100% MIT

bmad-loop-resolve

30

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Interactive escalation-resolution workflow for the bmad-loop orchestrator. A bmad-loop run paused on a CRITICAL escalation (a contradiction or gap a dev/review session could not safely resolve alone); you and the human disambiguate the frozen spec so the story can be re-driven. Invoked as /bmad-loop-resolve . Unlike…

not rated 5 9d ago A 97 tokens original MIT

bmad-loop-sweep

31

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Triage the deferred-work ledger for the bmad-loop orchestrator: verify every open entry against the actual codebase and return a machine-readable partition (bundles, already-resolved, blocked, skip, human decisions). Also migrates legacy pre-DW-format ledgers when invoked with --migrate. Automation-only — invoked by…

not rated 5 9d ago A 82 tokens original MIT

bmad-loop

32

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Iterate over a list of story keys, executing dev → review → PR → CI → merge for each. Use when the user says "loop these stories [list]" or "run the loop on [story keys]".

not rated 5 9d ago A 48 tokens original MIT

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Conduct market research on competition and customers. Use when the user says they need market research.

not rated 5 9d ago A 23 tokens copy · 81% MIT

bmad-party-mode

34

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Orchestrates lively group discussions between installed BMAD agents or custom personas, and helps author custom parties. Use when the user requests party mode, a roundtable, or multiple agent perspectives — or wants to create/configure a party, define personas, or build an AI focus-group panel.

not rated 5 9d ago A 63 tokens copy · 94% MIT

bmad-prd

35

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Create, update, or validate a PRD. Use when the user wants help producing, editing, or validating a PRD.

not rated 5 9d ago A 31 tokens copy · 100% MIT

bmad-prfaq

36

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Working Backwards PRFAQ challenge that stress-tests a product concept customer-first. Use when the user requests to 'create a PRFAQ', 'work backwards', or 'run the PRFAQ challenge'.

not rated 5 9d ago A 44 tokens copy · 94% MIT

bmad-product-brief

37

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief.

not rated 5 9d ago A 31 tokens copy · 100% MIT

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Generate end to end automated tests for existing features. Use when the user says "create qa automated tests for [feature]".

not rated 5 9d ago A 35 tokens copy · 95% MIT

bmad-quick-dev

39

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that follow the project's existing architecture, patterns and conventions. Use when the user wants to build, fix, tweak, refactor, add or modify any code, component or feature.

not rated 5 9d ago A 63 tokens copy · 73% MIT

bmad-retrospective

40

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Post-epic review to extract lessons and assess success. Use when the user says "run a retrospective" or "lets retro the epic [epic]".

not rated 5 9d ago A 38 tokens copy · 92% MIT

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Walk every branching path and boundary condition in content, report only unhandled edge cases. Orthogonal to adversarial review - method-driven not attitude-driven. Use when you need exhaustive edge-case analysis of code, specs, or diffs.

not rated 5 9d ago A 55 tokens original MIT

bmad-shard-doc

43

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Splits large markdown documents into smaller, organized files based on level 2 (default) sections. Use if the user says perform shard document.

not rated 5 9d ago A 34 tokens copy · 100% MIT

bmad-spec

44

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Distill any intent input into the SPEC kernel + companions — the canonical, preservation-validated machine contract for downstream work. Use when the user says "create a spec", "distill this into a spec", "validate this spec", or "update the spec".

not rated 5 9d ago A 57 tokens copy · 100% MIT

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Generate sprint status tracking from epics. Use when the user says "run sprint planning" or "generate sprint plan".

not rated 5 9d ago A 31 tokens copy · 92% MIT

bmad-sprint-status

46

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Summarize sprint status and surface risks. Use when the user says "check sprint status" or "show sprint status".

not rated 5 9d ago A 31 tokens copy · 95% MIT

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Conduct technical research on technologies and architecture. Use when the user says they would like to do or produce a technical research report.

not rated 5 9d ago A 31 tokens copy · 81% MIT

bmad-ux

48

mmornati/leanproxy-mcp

Skill Claude CodeCodex

Plan UX patterns and design specifications. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX".

not rated 5 9d ago A 37 tokens copy · 86% MIT

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: