Choose Subagent — AI skill for Claude Code
Decide which subagent type/model fits a task before spawning an Agent call.
How to install Choose Subagent
Installs to ~/.claude/commands/awcameron-skills-choose-subagent.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/awcameron/skills/HEAD/.claude/commands/choose-subagent.md -o ~/.claude/commands/awcameron-skills-choose-subagent.md Restart Claude Code, or start a new session, for it to be picked up.
What Choose Subagent does
description: Decide which subagent type/model fits a task before spawning an Agent call
Invoke the awcameron-skills:choose-subagent skill before spawning a subagent for: $ARGUMENTS
Classify by what the task actually *does* (does it write anything?), not by its topic. Read-only tasks (review, audit, investigate) belong on a read-only/exploration agent or a cheaper model; write tasks (implement, commit, open a PR) belong on the default write-capable agent, escalated to a stronger model o
Alternatives in AI
- Model Update — 增量更新财务模型 — 用新财报/新指引/修正假设重算 DCF 内在价值、Comps 隐含价、投资逻辑与目标价,输出 before→after delta 6.6k ★
- Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
- Paritok 4b V1 — Non-destructive compression gateway for AI coding agents 1.4k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Swarm Plan
Route ANY subagent-spawning task to the right vector, tier, and pins before spawning anything — the general pr
Claude Custom Review
Interactive Claude review — choose personalities and model before review starts. Shortcut for claude-review in
Agent Dispatch
Free skill for Claude Code, Cursor and any agent client: picks the model for each subagent by the type of task
Opensecretmask
Secret masking for Claude Code. Every credential becomes a format-preserving fake before the model reads it, a
Ask Kilo
Get an advisory second opinion from an external non-Claude model via the kilo CLI. Prompt-only — kilo never se
Warden Receipt
Show token-warden rule receipts — the per-rule verdict card with token savings vs. rent, per-task pass/fail, t
Related Agents
Type Curator
Selects a render-safe typography direction that fits the story, density, language, and reference DNA before co
Sf AI Architect
AI Architect of the Software Factory cell. Use whenever a project has an ML/DL/agentic-AI component, to decide
Bnb Explorer
Reconnaissance agent that scouts a user prompt and the target repository to assess scope before a break/bake w