Skip to content

minimax-ai/ronny

v0.2.5

Daily workflows and self-check skills from the MiniMax Code R&D lead: independent review, subagent split checks, tool and context budget audits, long sessions, long commands, harness experiments, trajectory review, plus everyday engineering practice for code review, review comments, small PRs, change descriptions and emergency changes.

ronny

The first stack in MCode Stack: the workflows and self-check skills of Ronny, R&D lead of MiniMax Code. Most skills pair with an article in the MCode Engineering Notes series (see ../../notes/).

Install

In Claude Code, one command installs this stack. In a shell:

claude plugin install ronny --marketplace MiniMax-AI/mcode-stack

Inside a session:

/plugin install ronny --marketplace MiniMax-AI/mcode-stack

Older Claude Code can add the marketplace first, then install:

/plugin marketplace add MiniMax-AI/mcode-stack
/plugin install ronny@mcode-stack

In Codex, add the marketplace, then install from the Plugins Directory or the CLI:

codex plugin marketplace add MiniMax-AI/mcode-stack
codex plugin add ronny@mcode-stack

In MiniMax Code, copy this whole directory into the local plugin directory shown by mcode plugin marketplace list, or copy single skills into ~/.agents/skills/. See the repository README.

Skills

SkillWhat it doesNotes
independent-reviewReview a diff from a clean context: only diff, requirement and test results; structured findings verified before fixing01
subagent-split-checkDecide whether work goes to a subagent or stays in the main loop; merge existing subagents back step by step01
harness-experimentRun a harness change as an experiment: small eval, one change, repeated runs, flipped tasks01, 02, 05
tool-budget-auditMeasure what tools cost in context and pick between trimming, tool search and programmatic tool calling02
long-session-checkDrop, summarize or write to file; when to compact vs. start fresh; review compaction and memory design03
handoff-docWrite a hand-off doc (goal, decisions, ruled out, next step) so a new session can pick up01, 03
long-command-checkTen-point audit of how an agent runs long shell commands and background tasks04
context-tax-auditInventory what is injected into every request and how it affects the prompt cache05
trajectory-reviewReview how the agent got its result, not only whether it passed-

Engineering practice

Everyday engineering skills, also published in agentara/skills and adapted from Google Engineering Practices (CC-BY 3.0). See NOTICE.md for licenses.

SkillWhat it does
engineering-code-reviewReview a change for code health: design, functionality, complexity, tests, approval risk
engineering-review-commentsWrite clear, severity-labeled review comments that explain the reasoning
engineering-review-feedbackHandle reviewer comments as the author: fix, clarify, resolve disagreements
engineering-small-prsSplit large features, refactors and migrations into small reviewable PRs
engineering-change-descriptionsWrite PR and commit descriptions that say what changed and why
engineering-emergency-changesDecide whether a hotfix is a real emergency and run expedited review safely

Plain-text versions of the checklists live in checklists/.