maestra

What maestra does, in the publisher's words

From the project README, punctuation lightly normalized · Open the README on GitHub →

Links

• github.com/phni3j9a/maestra-codex-plugin
• plugins/maestra/plugin.json (manifest)

Skills · 7

doctor

Verify Maestra prerequisites, exact Codex multi-agent routing, Git state, and version-bound runtime configuration before execution. Use only when the user explicitly invokes $maestra:doctor. This diagnostic must not activate the Maestra workflow or modify product code.

finish

Complete a Maestra project with risk-based final verification/review, Main Sol final semantic gate, and a user-facing report. Use only by direct explicit invocation or when Main routes here after every Run in an explicitly activated using-maestra workflow has passed its Gate.

gate

Perform the Main Sol semantic and architectural gate after a Maestra Run or PLAN_GAP. Use only by direct explicit invocation or when Main routes here from an explicitly activated using-maestra workflow or Run. Direct invocation is for recovery/re-evaluation and does not activate the workflow.

plan

Create the full detailed implementation plan for an approved Maestra specification in Main Sol. Use only by direct explicit invocation or when Main routes here from an explicitly activated using-maestra workflow. Main owns architecture, implementation strategy, Task decomposition, target files, and…

run

Execute exactly one approved Maestra Run using a fresh Terra execution orchestrator. Use only by direct explicit invocation or when Main routes here from an explicitly activated using-maestra workflow. Terra may coordinate, verify, adjudicate review, and commit, but must return PLAN_GAP instead of…

spec

Turn an already-discussed software change into a concise, user-approvable Maestra specification. Use only by direct explicit invocation or when Main routes here from an explicitly activated using-maestra workflow. Do not execute implementation work or spawn implementation agents.

using-maestra

Activate and conduct the complete Maestra development workflow for the current task and thread. Use only when the user explicitly invokes $maestra:using-maestra; installing Maestra, ordinary development prompts, doctor, or direct phase-skill recovery must never activate this workflow.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

Category

Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Keywords

codex · multi-agent · orchestration · context-isolation · review

Related by publisher and keywords

• axiomphni3j9a

  Codex engineering with Astra XHIGH planning and advice, Luna MAX Fast workers, Sol MAX design, independent Sol review, and context isolation.

• bernsteinsipyourdrink-ltd

  The open-source governance layer for AI agents. Spawn parallel agents in per-task git worktrees, verify their work, and merge results; no model in the coordination loop, so replaying a plan reproduces its task graph byte-identically.

• dialecticslior

  Configuration-first multi-agent design debate. Agents with different roles (architect, security, performance, simplicity,...) run structured debate rounds and a judge decides when convergence is reached.

• codex-skillscoryparrry

  Agent skills for research, App Store readiness, Codex model routing, repository and Swift review, PR feedback triage, and safe branch cleanup.

• luna-factoryjoshyorko

  Luna-first orchestration for economical delegation, bounded escalation, and evidence-backed completion.

• caoawslabs

  Drive CLI Agent Orchestrator multi-agent sessions from any Agent-Plugins-compatible client. Prerequisites: the `uv` toolchain must be on PATH (the MCP server is launched via `uvx`), and a CAO API server must be running locally at http://127.0.0.1:9889 (`cao-server`). All communication is localhost-only.