compose:subagent

compose:subagent is a skill for Claude Code, Codex from XiaomiMiMo/MiMo-Code. It costs 17 tokens per session (3,473 once invoked), scanned A, original, MIT.

A workflow for carrying out an implementation plan by assigning separate tasks to fresh helper agents and reviewing each result.

In plain words
What is it for?
Executing multi-step plans, delegating independent implementation tasks, and reviewing completed work before moving on.
Why use it?
It keeps each task focused and adds checks for both requirement compliance and code quality during development.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Executing multi-step plans, delegating independent implementation tasks, and reviewing completed work before moving on.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xiaomimimo/mimo-code/subagent
About the project

MiMoCode is a terminal-based AI coding assistant that reads and writes code, runs commands, manages Git, and remembers project context across sessions. Developers use it to work with software projects through a command-line interface and connect it to language-model providers; the catalogue includes skills and instructions for it.

XiaomiMiMo/MiMo-Code · 12,961 stars · on GitHub · mimo.xiaomi.com

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add XiaomiMiMo/MiMo-Code --skill subagent
Clone the repo
git clone --depth 1 https://github.com/XiaomiMiMo/MiMo-Code

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for compose:subagent

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaomimimo/mimo-code/subagent/github.svg)](https://agentmods.dev/skills/xiaomimimo/mimo-code/subagent)
Your own site
<a href="https://agentmods.dev/skills/xiaomimimo/mimo-code/subagent"><img src="https://agentmods.dev/badge/skills/xiaomimimo/mimo-code/subagent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for compose:subagent

Your own site · 80×15
<a href="https://agentmods.dev/skills/xiaomimimo/mimo-code/subagent"><img src="https://agentmods.dev/badge/skills/xiaomimimo/mimo-code/subagent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,473 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 30
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.03473
Opus 5 $0.00009 $0.01736
Sonnet 5 $0.00003 $0.00695
Haiku 4.5 $0.00002 $0.00347

Measured 5d ago against content hash ea3fe06ccc2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

compose:subagent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

packages/opencode/src/skill/compose/.bundle/subagent/SKILL.md · 325 lines

How it starts

The opening of the file, as written. The whole thing — 325 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent-Driven Development

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

Why subagents: You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration

Continuous execution: Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are: BLOCKED status you cannot resolve, ambiguity that genuinely prevents progress, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it. When you must stop for ambiguity or a blocker, use compose:ask to present the situation with structured options. If no user is available, resolve it with your best judgment and continue.

When to Use

  1. Have implementation plan? — No → brainstorm first or manual execution
  2. Tasks mostly independent? — No (tightly coupled) → brainstorm first or manual execution
  3. Stay in this session? — Yes → compose:subagent / No → compose:execute (parallel session)

vs. Executing Plans (parallel session):

  • Same session (no context switch)
  • Fresh subagent per task (no context pollution)
  • Two-stage review after each task: spec compliance first, then code quality
  • Faster iteration (no human-in-loop between tasks)

The Process

Setup: Read plan → extract all tasks with full text → note context → create a task per plan task (task create)

Per Task:

  • Dispatch implementer — create+bind task (--task <TID>, auto-starts), inject covered spec as Intent, dispatch (./implementer-prompt.md)
  • Implementer asks questions? — Yes → answer, provide context, re-dispatch implementer
  • Implementer implements — tests, commits, self-reviews
  • Spec review phase 1 — dispatch with spec + diff only, no report
  • Phase 1 flagged anything? — Yes → dispatch phase 2 (report explains flags, downgrade-only)
  • Spec gate: all in-scope claims pass with evidence? — No → implementer fixes → back to spec review phase 1
  • Code quality review — dispatch reviewer (./code-quality-reviewer-prompt.md)
  • Quality approved? — No → implementer fixes → back to code quality review
  • Mark task donetask done <TID>

Read the full file on GitHub · 325 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 325 lines · 17 tokens per session scan A ea3fe06ccc2e

Subscribe to this mod's changes

compose:subagent is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (12,961 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 3,473 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.