Skills for Real Engineers. Straight from my .agents directory.
mcode-delegate
Agent skill fromamElnagdy/delegate-skills
Delegate a coding task to the MiniMax Code CLI (`mcode`) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to MiniMax Code or a MiniMax model — phrasings like "have MiniMax do X", "delegate this to mcode", "run it through MiniMax Code", or "use MiniMax to implement/fix/refactor" — or to run a queue of coding tasks through MiniMax Code while staying the reviewer. DO NOT USE for tasks small enough to do inline, or when the user wants the code written directly without delegating.
How to install mcode-delegate
npx skills add amElnagdy/delegate-skills# or add only this skill to Claude Code: copy the folder
skills/mcode-delegate/
# into
~/.claude/skills/mcode-delegate/ (all projects)
.claude/skills/mcode-delegate/ (one project)
1# MiniMax Code Delegate23You are the **orchestrator**. This skill lets you hand a bounded coding task to a separate4**implementer** — the MiniMax Code CLI (`mcode`) — then review what it produced and land it yourself.5You write the brief and own the judgment; MiniMax Code does the typing in your working tree; you6verify and commit.78Nothing here is specific to one orchestrating agent. The loop needs only the ability to run a shell9command and read a file, so it works the same whether you are Claude Code, OpenCode with a selected10model, or any comparable agent. (It is designed for and run on Claude Code; treat other orchestrators11as designed-for, not yet proven.)1213## When NOT to use this1415- The task is small enough to just do inline — delegation overhead is not worth it.16- `mcode` is not installed or not signed in (run `mcode login`, or `mcode login --region global`).17- You want to write the code yourself, or you only need a review of local changes (`mcode exec review`18 does that directly).19- You need writes outside the target tree to be impossible, not just unlikely. MiniMax Code has no20 sandbox; use an OS-enforced one such as `codex-delegate`, or run this inside a container.2122## Read this before the first dispatch: the autonomy model2324`mcode exec` takes a permission policy — `smart`, `full`, or `off` — and has **no sandbox and no25read-only or plan setting** for a headless run (`ask` needs the TUI or ACP).26…
Excerpt shown under the repository's MIT license.
More skills in delegate-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
