claude

muse

Use Muse Code from Claude Code to review code or delegate tasks.

0 on GitHubby Dennis Nasarovv0.1.0MITupdated 4 days ago
/

Plugin muse from marketplace ph3on1x in ph3on1x/agent-plugins-skills. Commands read from the repo's manifest — 4 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (3)

  • muse-cli-runtime

    Internal helper contract for calling the muse-companion runtime from Claude Code

  • muse-prompting

    Internal guidance for shaping task prompts sent to Meta's Muse Code (Muse Wonder and Muse Spark models) by the muse rescue subagent

  • muse-result-handling

    Internal guidance for presenting muse helper output back to the user

Slash commands (8)

  • /muse:adversarial-review

    Run an Muse Code (muse) review that challenges the implementation approach and design choices

  • /muse:cancel

    Cancel an active background Muse Code (muse) job in this repository

  • /muse:rescue

    Delegate investigation, an explicit fix request, or follow-up rescue work to the Muse Code (muse) rescue subagent

  • /muse:result

    Show the stored final output for a finished Muse Code (muse) job in this repository

  • /muse:review

    Run an Muse Code (muse) code review against local git state

  • /muse:setup

    Check whether the local Muse Code CLI (muse) is ready and optionally toggle the stop-time review gate

  • /muse:status

    Show active and recent Muse Code (muse) jobs for this repository, including review-gate status

  • /muse:transfer

    Transfer the current Claude Code session to Muse Code so it can be resumed there

Subagents (1)

  • muse-rescue

    Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass from a different model family, needs a deeper root-cause investigation, or should hand a substantial coding task to Meta's Muse Code (Muse Wonder or Muse Spark) through the muse runtime

Hooks (3)

  • SessionStart

    node "${CLAUDE_PLUGIN_ROOT}/scripts/muse-companion.mts" hook SessionStart

  • SessionEnd

    node "${CLAUDE_PLUGIN_ROOT}/scripts/muse-companion.mts" hook SessionEnd

  • Stop

    node "${CLAUDE_PLUGIN_ROOT}/scripts/muse-companion.mts" hook Stop

View source on GitHub

More from ph3on1x/agent-plugins-skills

All 9 plugins →

agy

claude

Use Antigravity from Claude Code to review code or delegate tasks.

3 skills · 7 commands · 1 agent · hooks

0

wisci

claude

WISCI context engineering framework — Write, Isolate, Select, Compress, Iterate. Context store (.wisci/) whose notes quote their code evidence, checked on every load, per-stream handoffs (every compaction summary is one), session hooks, and commits with AI-Context trailers.

5 skills · hooks

0

cmux

claude

Skill for orchestrating independent Claude Code sessions in cmux terminal — split panes, agent monitoring, browser automation, sidebar metadata, notifications, and full CLI coverage.

1 skill · hooks

0

adveloop

claude

GAN-inspired adversarial dev loop — Planner sequentially drives a Generator and Evaluator in fresh cmux panes, with a hard pass/fail gate per deliverable. Adapted from Anthropic's harness-design guidance for long-running agentic apps.

1 skill

0

refine-prompt

claude

Interview-style prompt refiner that picks a framework, fills gaps via AskUserQuestion, assembles a structured XML prompt, confirms, then executes it. In Claude Code, adds a refine prompt button above the prompt box.

1 skill

0

relamo

claude

Recursive Language Model skill — programmatic codebase exploration via persistent Python REPL loop

1 skill

0

Maintain muse?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins9 plugins