subagent-split-check SKILL.md skillA

subagent-split-check from minimax-ai/mcode-stack is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add minimax-ai/mcode-stack/subagent-split-check@git:20261028.c889a19

Pins git:20261028.c889a19 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
minimax-ai/mcode-stack
Path
stacks/ronny/skills/subagent-split-check/SKILL.md
Versions recorded
1
Latest version
git:20261028.c889a19, committed Oct 28, 2026
Size
3,587 bytes
Repository stars
495
License
MIT

Decide whether a piece of work should go to a subagent or stay in the main agent loop. Use before spawning subagents, when designing a multi-agent architecture, or when auditing an existing set of subagents for merging back.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Subagent Split Check

Subagents are a tool for managing context, not for dividing up territory.
Default to one main loop with skills loaded on demand. Split only when one
of the conditions below is clearly met.

Companion to MCode Engineering Notes 01, "More subagents isn't better".
Plain-text checklist: `checklists/subagent-split.md`.

## 1. Is there a context reason to split?

Split is worth considering only if at least one is true:

1. **Measured degradation.** The single loop gets measurably worse because
   its context grows. "Measured" means eval results, not a feeling.
2. **Parallel, disposable work.** Several pieces of work can run in parallel,
   each needs a clean context, and each can be thrown away when done (for
   example independent research threads).
3. **Tool or instruction conflict.** The main agent keeps picking the wrong
   tool, or its instructions conflict with each other.

Then ask the deciding question for the specific step: **will we need the raw
intermediate output later, or only a conclusion?** Only "just the conclusion"
work is a good fit for a subagent.

If the reason is "this belongs to another team" or "this is a different kind
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add minimax-ai/mcode-stack/subagent-split-check@sha256:367205b2f6f0a872

The line at the top of this page pins the label git:20261028.c889a19, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_7ya4s2uhjaclgfjl.svg)](https://markdownregistry.com/a/art_7ya4s2uhjaclgfjl)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 28, 2026.

versioncommittedcommitsizeaudit
git:20261028.c889a19 latest2026-10-28 c889a19 3,587 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3587 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

minimax-ai/mcode-stack · 495 stars · license MIT · pushed 2026-10-29 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_7ya4s2uhjaclgfjl
GET https://markdownregistry.com/api/v1/resolve?ref=minimax-ai/mcode-stack/subagent-split-check
GET https://markdownregistry.com/api/v1/blob/367205b2f6f0a8729d18b619e3c11c5d835e8816b77e9149aefd5aed5e2f87fd

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from minimax-ai/mcode-stack

lifting-loops SKILL.md skill
minimax-ai/mcode-stack · stacks/jiachen/skills/lifting-loops/SKILL.md · Finds loops where the user keeps acting as a manual step for agents (retrying, judging output, approving, carrying…
git:20261028.e7307b0 · audit A · 495 stars
making-content SKILL.md skill
minimax-ai/mcode-stack · stacks/jiachen/skills/making-content/SKILL.md · Content production in three modes: rewrite, Xiaohongshu (小红书) image post, short video. Rewrite (default): turns an…
git:20261028.e7307b0 · audit A · 495 stars
context-tax-audit SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/context-tax-audit/SKILL.md · Inventory everything an agent injects into each request besides the user's message, such as system prompt, environment…
git:20261029.49a3ff4 · audit A · 495 stars
engineering-change-descriptions SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/engineering-change-descriptions/SKILL.md · Use when writing, rewriting, or reviewing PR/CL descriptions, commit messages, or code-change summaries that explain…
git:20261028.c6ee606 · audit A · 495 stars
engineering-code-review SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/engineering-code-review/SKILL.md · Use when reviewing code, pull requests, patches, CLs, diffs, or proposed implementations for engineering quality, code…
git:20261028.c6ee606 · audit A · 495 stars
engineering-emergency-changes SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/engineering-emergency-changes/SKILL.md · Use when a code hotfix, rollback alternative, production/security/legal fix, launch blocker, or hard external deadline…
git:20261028.c6ee606 · audit A · 495 stars
engineering-review-comments SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/engineering-review-comments/SKILL.md · Use when drafting, rewriting, classifying, or improving code review comments as a reviewer. TRIGGER on rough review…
git:20261028.c6ee606 · audit A · 495 stars
engineering-review-feedback SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/engineering-review-feedback/SKILL.md · Use when handling code review feedback as the change author, addressing reviewer comments, drafting replies, resolving…
git:20261028.c6ee606 · audit A · 495 stars
engineering-small-prs SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/engineering-small-prs/SKILL.md · Use when planning, splitting, shrinking, or sequencing large features, refactors, migrations, or pull requests into…
git:20261028.c6ee606 · audit A · 495 stars
handoff-doc SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/handoff-doc/SKILL.md · Write a hand-off document so a fresh session or another person can continue the current task without the chat history…
git:20261028.c889a19 · audit A · 495 stars
harness-experiment SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/harness-experiment/SKILL.md · Run a harness change as a controlled experiment, with a small end-to-end eval, one change at a time, repeated runs, and…
git:20261029.49a3ff4 · audit A · 495 stars
independent-review SKILL.md skill
minimax-ai/mcode-stack · stacks/ronny/skills/independent-review/SKILL.md · Review a code change from a clean context, the way an outside reviewer would. Use after the agent finishes an…
git:20261028.c889a19 · audit A · 495 stars

Every file in minimax-ai/mcode-stack

Browse by kind, by grade A, or by owner.