Gives a coding agent a repeatable path from a clear change request to a checked result. It implements fixes without weakening tests, can deliver an independent go or no-go verdict on finished work, and keeps project memory so the next session starts with context.
@boshu2Dispatch independent tasks to parallel workers or subagents without write collisions. Use when: running or planning agents in…
@boshu2Run a supplied task in headless AGY (Antigravity, Gemini) and collect its result. Use when: AGY, Antigravity or Gemini is…
@boshu2Compare interface designs and find structural friction. Use when: a change spreads across modules or a boundary is unclear. For…
@boshu2Run one prompt through headless Claude with scoped permissions and a time bound. Use when: scripting or automating a `claude -p`…
@boshu2Run one prompt through headless Codex and capture the result. Use when: wanting a one-shot `codex exec` run or CI step. Not for…
@boshu2Compare independent opinions from several models or contexts without inflating agreement. Use when: wanting a second opinion or…
@boshu2Draft or lint a bounded long-running goal prompt with a finish line and hard limits. Use when: asked to craft or lint a goal (a…
@boshu2Write source-checked docs, READMEs, change descriptions and handoffs. Use when: documenting a change, leaving or resuming a…
@boshu2Settle what domain terms mean per context, and which repository conventions or language standards (Go, Python) apply. Use when:…
@boshu2Audit CLI, API, MCP or SDK discovery, first use and error recovery. Use when: designing an agent-facing tool or investigating…
@boshu2Brainstorm evidence-backed options for what to build, or stress-test an idea. Use when: deciding what to build next, comparing…
@boshu2Change or repair code, config or services without weakening tests; report what ran and what did not. Use when: implementing a…
@boshu2Read large files or many files on the caller's behalf and return short line-referenced summaries with coverage. Use when a file…
@boshu2Expert code review specialist. Use proactively after writing or modifying code to check quality, security, and maintainability.
@boshu2Write one file from a spec plus a required reference file, matching the reference's patterns, and return a receipt (path, line…
@boshu2You are the Opus-medium overflow executor for one claimed implementation step.
@boshu2Deep codebase exploration and analysis. Use for understanding code architecture, finding patterns, and gathering context before…
@boshu2Is this you? Claim your profilePut a plugin at the top of Plugins, from $9
