Skip to main content
Glama
BenjaminNH

workbuddy-subagent-bridge

by BenjaminNH

Related Servers

Alternatives to workbuddy-subagent-bridge

No user-submitted related servers found.

    Related Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables AI coding agents like Claude Code, Codex, Cursor, and OpenCode to delegate tasks to the WorkBuddy CLI as a sub-agent via an MCP tool, with one-command setup and configurable model/permission options.
      1
      103 npm
      5
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Enables any MCP host to delegate work to multiple coding-agent CLIs such as Codex, Claude Code, and Antigravity as subagents, preserving native sessions and supporting team-based supervision and agent-to-agent messaging.
      17
      7 npm
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Lets any MCP-compatible client run reusable Markdown-defined coding agents through a chosen backend CLI, returning their results to the same conversation. It enables delegation of coding tasks, shared agent definitions, permission modes, and cross-call session continuation.
      294 npm
      MIT

    TDQS

    A3.5/5.0

    Scored across 10 tools

    Disambiguation4/5

    Most tools target distinct session actions (start, send, cancel, close, permission reply, report) and are easy to tell apart. The only potential confusion is between workbuddy_session_status (per-session state) and workbuddy_status (persisted task registry), which are related but serve different purposes.

    Naming Consistency4/5

    All tools share the workbuddy_ prefix and mostly follow a predictable pattern: workbuddy_session_<verb> for session operations, plus standalone nouns (status, models, doctor). The mix of verb-based session actions with noun-only utility tools is a minor deviation, but the overall convention is clear.

    Tool Count5/5

    Ten tools is well within the ideal range for a session-bridge server and each one maps to a distinct lifecycle stage or utility concern. No tool feels redundant or unnecessary for the stated purpose.

    Completeness4/5

    The session lifecycle is well covered: start, send, status, cancel, close, permission reply, and report. The persisted task listing, model enumeration, and environment diagnostic round out the surface. Minor gaps exist, such as no explicit session resume or task-triggered report fetch, but agents can generally work around these.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues