Skip to main content
skill CX Codex

subagent-split-check — Claude Code skill: install and use

subagent-split-check is a Claude Code skill that decides whether work belongs in a subagent or the main loop. It checks context boundaries before a split.

MIT ★ 741 updated 2026-11-11

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add MiniMax-AI/mcode-stack
/plugin install ronny@mcode-stack
Open on GitHub

What subagent-split-check does

The subagent-split-check skill reviews a task before a subagent is created and returns a keep-or-split decision. It looks for measured quality loss from context growth, parallel disposable work, and conflicts between tools or instructions.

A valid split has a clear context boundary: the subtask has little dependence on the rest of the system and returns a verdict, list, or small structured result. The skill first checks cheaper fixes, such as grouping tools by intent, moving procedures into skills, and writing state to a document. Existing subagents can be merged one at a time and compared with end-to-end evaluations.

What it helps with

  • decide whether a task belongs in a subagent
  • draw a context boundary around a subtask
  • find cheaper fixes before adding another agent
  • compare a merged loop with an existing subagent setup

Example prompts for the agent

  • Decide whether the API verification should stay in the main loop or move to a subagent.
  • Audit this multi-agent design and identify which subagents should be merged.
  • For this task, state the split condition, the boundary, and the measurement needed to validate it.

How to install subagent-split-check

1Plugin marketplace

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

This installs the whole ronny plugin with all its skills

2Skills CLI (Vercel)

npx skills add MiniMax-AI/mcode-stack --skill subagent-split-check -a claude-code

3Manually: put the files in place

~/.claude/skills/subagent-split-check/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/subagent-split-check/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about subagent-split-check

How do I install subagent-split-check in Claude Code?

Run /plugin marketplace add MiniMax-AI/mcode-stack in Claude Code, then run /plugin install ronny@mcode-stack.

What does subagent-split-check do?

It decides whether a task should stay in the main loop or move to a subagent. It also defines the split boundary and names the measurement needed to validate the choice.

When does subagent-split-check support using a subagent?

When context growth has measurably reduced results, independent disposable tasks can run in parallel, or tools and instructions conflict. The subagent should return a compact result rather than raw intermediate work.

Source text

SKILL.md · MIT
---
name: subagent-split-check
description: 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.
---

# 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
of question", do not split. That leads to lossy hand-offs between agents.

## 2. If you split, cut along context boundaries

- The subtask barely depends on the rest of the system.
- It returns a compact result (a verdict, a list, a small structured object).
- Good examples: independent research threads, a component with a clear
  interface, a black-box verification step.
- Expose the subagent to the main agent as a tool, so the main agent keeps
  the conversation with the user. Hand the whole conversation over only if the
  subagent truly has to talk to the user directly.

## 3. Before splitting, check the cheaper fixes

- **Too many tools?** Merge tools by user intent and defer rarely used ones
  behind tool search (see `tool-budget-audit`).
- **Prompt too big?** Turn procedures and rules into skills, actions and live
  data into tools, and reference material into something loaded on demand.
- **Worried about losing state?** Write the plan, decisions and review
  conclusions into a design or progress doc (see `handoff-doc`). Once state
  lives in a file, the session can be cleared safely, and the urge to split
  "to protect context" mostly goes away.

## 4. Merging existing subagents back

If a system already has many subagents:

1. Build a small end-to-end eval first. A handful of golden examples is enough
   to start.
2. Merge the most frequently used, most tightly coupled ones first: those
   called back to back, reading and writing the same data, or feeding each
   other's input.
3. During the transition, wrap remaining subagents as tools for the main
   agent, which also gives you a baseline.
4. Merge one at a time: its prompt becomes a skill, its API calls become tools.
5. Compare before and after. Look at which tasks flipped, not only the total
   score, and run each task more than once.
6. Keep the subagent only if the merged version is measurably worse.

Use `harness-experiment` for the measuring discipline.

## Output

Answer with: split or keep in the main loop, the condition that justifies it
(or "none met"), where the boundary is if splitting, and what you would
measure to confirm.

© Ronny (MiniMax Code team) · MIT · MiniMax-AI/mcode-stack

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set27

The whole set →
independent-review independent-review is a Claude Code skill that reviews changes from a clean context before merge. It compares the diff with the requirement and test output. CX Codex +1 ★ 741repo stars agent-brief The agent-brief skill for Claude Code structures task delegation to AI agents. It forces clarity on stakes, hypotheses, and verification criteria before an agent starts working. CX Codex +1 ★ 741repo stars evidence-first-review evidence-first-review is a Claude Code skill that audits an agent’s finished work from command logs and test evidence. It runs before a PR merge or an analysis is accepted. CX Codex +1 ★ 741repo stars pr-description pr-description is a Claude Code skill that drafts and verifies pull request descriptions for GitHub and GitLab. It runs when opening a PR or when MCode Review reports missing sections. CX Codex +1 ★ 741repo stars context-tax-audit The context-tax-audit skill for Claude Code inventories injected data in agent requests to reduce token usage. It identifies redundant prompt blocks and configurations that hinder prompt cache performance. CX Codex +1 ★ 741repo stars long-session-check long-session-check is a Claude Code skill that audits long-session context and memory handling. It starts when constraints get lost or compaction has happened several times. CX Codex +1 ★ 741repo stars long-command-check long-command-check is a Claude Code skill that audits shell command execution in agent harnesses. It checks dev server hangs, timeouts, backgrounding, and prompt cache expiration. CX Codex +1 ★ 741repo stars tool-budget-audit tool-budget-audit is a Claude Code skill that measures context used by tool schemas and call results. It flags catalog bloat and mistaken tool choices. CX Codex +1 ★ 741repo stars

Project sponsors

Companies that keep this analytics open