choosing-subagent-models
Use when about to launch any subagent — a research or exploration agent, a reviewer, an implementer, a parallel fan-out, or a fork.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- choosing-subagent-models
- description
- Use when about to launch any subagent — a research or exploration agent, a reviewer, an implementer, a parallel fan-out, or a fork.
03 SKILL.md 正文
Choosing subagent models
Every spawn names its model. An omitted model inherits the session's: a lookup from an Opus
session runs at full price, a final review from a cheap session runs cheap, and neither says so.
- The kit's spawn hook refuses a launch with no
model. It never picks one — pick here, by the job, not by the model the session happens to run. - Use the aliases
haiku,sonnet,opus, not version IDs. They survive a model release.
The table
| The subagent's job | Model |
|---|---|
| Mechanical and fully specified — read a known file and extract a value, run a known test, build or lint command and report its output, summarize a log, apply a change whose exact text is given — where one command proves it done | haiku |
| Gathering — web research, codebase exploration, "where is X", reading code to answer a question, implementing a plan task whose code is written out, reviewing one task's diff | sonnet |
| Judgment — design and architecture, debugging after a fix has already failed, security review, the final review of a branch, implementing from prose where decisions are still open | opus |
Where the lines fall
- Haiku gets no search. Unclear where to look, or what the thing is called, makes it research —
sonnet. A file haiku fails to find comes back as a confidently incomplete answer. - Haiku stops at its first failure — a failed command, an edit that does not apply, unexpected
output. Re-spawn on
sonnet; do not retry. Cheap models take 2–3× the turns on multi-step work and cost more overall. A red run fromvvkit:test-runneris its result, not its failure. - Sonnet is the floor for anything that decides correctness: every reviewer, every implementer that must make a test pass.
- Research fleets stay on
sonnet, even for an architectural question. Readers gather; the judgment happens in the main conversation. - Between two tiers, take the higher and say so. When the higher one is a real cost — a fleet, a long run — ask once, naming both tiers and what the higher one buys.
- Escalate, do not repeat. A blocked implementer or a fix loop that is not converging goes up a tier. The same spawn on the same model gives the same result.
- Two failed rounds end re-dispatching. Take the core back into the main conversation, or send a narrower piece one tier up. A wide brief that failed twice fails on scope, and a stronger model inherits the same ambiguity.
Special cases
- A fork runs on the parent's model and ignores
model. Fork only when the inherited context is worth the session's price. - A named agent whose definition sets
modelcarries its author's default for an ordinary job. Pass nothing when the table agrees; pass a tier up when the job is bigger — a whole branch, security-sensitive code. Never a lower one. - The user named a model. Theirs wins.
CLAUDE_CODE_SUBAGENT_MODELforces one model onto every subagent. A debugging tool, not a policy.KIT_SUBAGENT_MODEL_GATE=0turns the spawn hook off. The table still applies.
04 同仓库更多 Skills
no-heading
Use when proving that the validator rejects a body with no H1 and a force-loading @-link.
wrong-name-does-not-match-dir
Dispatches a subagent per task and reviews between each one.
writing-tests
Use when adding or changing behavior, fixing a bug, or judging whether an existing or generated test earns its place.
writing-skills
Use when authoring or editing a skill, agent, command or hook for this kit, or when deciding whether a piece of guidance belongs in a skill at all.
writing-project-instructions
Use when creating or editing a CLAUDE.md or AGENTS.md, when it has grown long, or when a rule in it also exists in an installed skill.
writing-logs
Use when adding or reviewing log statements, or when deciding what level a message belongs at.