Pick the model tier for every subagent before spawning it, so cheap work runs on cheap models: Opus for anything that writes, runs, implements, designs, or carries consequence; Sonnet for read-only work like research, reading, and summarizing; a Haiku swarm when fanning out more than five agents on a breadth sweep or brainstorm; and grok, on the separate Cursor meter, for token-heavy work whose answer you can check cheaply. Also checks the remaining Claude 5-hour and 7-day allowance and shifts checkable work to grok when either window runs low. TRIGGER — read BEFORE any subagent spawn, including agents you decided to spawn on your own initiative and `agent()` calls inside a Workflow. Do not skip it because the task "looks obvious" — the lane is a two-second check and the default is wrong half the time. Also fires on /dispatch, "spawn subagents", "fan out", "run these in parallel", "use a swarm of agents", "which model should this agent use", "route this to a smaller model".
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
Pick the model tier for every subagent before spawning it, so cheap work runs on cheap models: Opus for anything that writes, runs, implements, designs, or carries consequence; Sonnet for read-only work like research, reading, and summarizing; a Haiku swarm when fanning out more than five agents on a breadth sweep or brainstorm; and grok, on the separate Cursor meter, for token-heavy work whose answer you can check cheaply. Also checks the remaining Claude 5-hour and 7-day allowance and shifts checkable work to grok when either window runs low. TRIGGER — read BEFORE any subagent spawn, including agents you decided to spawn on your own initiative and `agent()` calls inside a Workflow. Do not skip it because the task "looks obvious" — the lane is a two-second check and the default is wrong half the time. Also fires on /dispatch, "spawn subagents", "fan out", "run these in parallel", "use a swarm of agents", "which model should this agent use", "route this to a smaller model".
license
MIT
metadata
{"author":"Mehdi Foroozandeh","version":"1.0"}
dispatch — the right worker for the job
A subagent inherits the main loop's model unless you say otherwise. That means a grep
across a directory and a database migration both run on Opus, and you pay Opus rates for
both. Most delegated work does not need the best model in the lineup.
The output-token spread is 10× end to end: Haiku $5/M, Sonnet $15/M, Opus $25/M, Fable
$50/M. That spread pays off on volume, not on any single call — so route every spawn, and
never agonize over one.
The lanes
Ask one question:
does this agent write or run anything?
Lane
model
When
Build
opus
Writes files, edits code, runs commands, implements, designs, works through complex logic, or produces a judgment you'll act on directly
Read
sonnet
Read-only. Search, research, market research, reading, extracting, summarizing, mapping a codebase. Sonnet never writes.
Swarm
haiku
Only inside a fan-out of more than five read-only agents dispatched in one batch, on a breadth sweep or brainstorm — where coverage matters more than any single agent's answer
A judgment the parent will act on is Build-lane even when nothing gets written — reconciling
conflicting sources, picking between options, deciding whether something is sound. Plain
extraction and summary stay in Read.
"One batch" means spawned together in a single dispatch. Eight agents run two at a time
across a task are eight Read-lane agents, not a swarm.
Opus is the ceiling. Never auto-route to fable; a subagent smarter than the parent
means judging output the parent could not have produced. It unlocks only when the user
writes the word — fable, or a specific model ID. A capability request ("use the best
model", "this one's hard, go all out") is not naming it: that caps at opus.
Haiku exists only in the swarm lane. A lone Haiku agent is never the right call — if
it's worth one agent, it's worth Sonnet.
The grok lane — a different meter
grok is not a fourth tier. It is a Grok 4.6 subagent on the Cursor subscription,
spawned through Bash, not through the Agent tool. Its work never touches the Claude
allowance; only the answer it hands back enters context. Measured on a whole-repo read:
291k tokens spent there, 4.7k returned here.
So route this lane by verifiability, not by strength. Send grok anything token-heavy
whose answer you can check cheaply — however hard it is:
whole-repo or whole-directory reads
log, output and test-failure sweeps
broad multi-file searches where only the conclusion comes back
first-draft implementations that ship with tests you will run
Keep on the Claude lanes anything you cannot cheaply check: design judgment, research
verdicts, anything writing to a crux vault, and any call where being subtly wrong costs
more than the tokens saved. Grok output is untrusted input — verify before acting.
grok -r -e high "..." read-only analysis (the default posture)
grok -e high "..." write and run enabled
grok -r -b brief.md "..." splice a written brief in
Effort per task: xhigh for deep analysis where the answer is the deliverable, high
by default, medium for mechanical sweeps, low for smoke tests only. Higher effort
spends the other meter, so when in doubt go up.
Grok runs in its own process and cannot see this conversation. A thin answer almost
always means a thin brief. Mechanics, brief format and failure modes are in
references/grok.md — read it before the first grok call of a session.
Quota gate
Before a batch that will spend real tokens, check what is left:
~/.claude/bin/claude-quota
Reading
Route
Fresh · 5-hour < 80% and 7-day < 75%
By the lanes above
Fresh · 5-hour ≥ 80% or 7-day ≥ 75%
Send every checkable Claude-lane agent to grok instead, and say why
Stale · missing · NO DATA
By the lanes above, and say "quota unknown" out loud
Gate at 80 rather than 95: the turn that checks the quota also spends it. The 7-day window
gets the tighter gate because it refills over days, not hours.
Never read a missing cache as "near the limit."NO DATA is the normal state on this
machine — the cache is only written when Claude Code invokes the custom statusLine
command, and the desktop app does not. Treating absence as a limit signal would route
everything to grok forever, silently.
Escalations
Four conditions override the lane and send the work to opus:
A lower lane already came back thin, wrong, or hedged. Retry one lane up. Do not
re-prompt the same tier with a firmer instruction — the tier was the problem. This
escalation stops at opus — it never reaches for fable. When an Opus agent comes
back thin, the model was not the bottleneck: rewrite the brief, split it into narrower
briefs, or do the work inline. Re-spawning on a sharper brief is fine — re-spawning
the same brief is what never works.
You can't tell which lane it is. Ambiguity resolves upward.
The brief is ambiguous or underspecified. An agent that must infer the goal needs
the judgment to infer it well.
A read feeds something security- or correctness-critical you won't re-verify.
Read-only does not mean low-stakes.
Everything else stays in its lane. Don't invent a fifth condition mid-task.
Depth
Do not set an effort parameter — subagents inherit the session's effort, and that's
correct. Shape depth through the prompt instead, which costs nothing:
Swarm agents: "Answer from the first solid match. Don't verify, don't survey alternatives."
Build agents on design or root-cause work: "Verify by a second method before returning."
Read agents: neither — let them work at their natural depth.
This rule is about the Agent tool. grok -e is a different knob on a different
meter — set it per task, as the grok lane says.
Say what you routed
Two things, both cheap:
One line before a batch, before the spawn calls: "7 haiku for the sweep, opus for
the implementation." When an escalation fired, name it in the same line: "opus — the
sonnet pass came back hedged."
A model tag in every agent's description, e.g. review:auth [opus], so the routing
is visible in the agent list without opening anything. Grok calls get the same tag in
the Bash description: sweep crux engine [grok:xhigh].
Mechanics
Per call on the Agent tool — model takes the bare tier name, not a full model ID:
Omitting model inherits the main loop. That is a routing decision too — make it on
purpose, not by forgetting.
What this is not
Not for the main loop. Dispatch routes subagents. Your own model is the user's choice.
Not a reason to spawn. If the work is faster done inline, do it inline. Routing a
subagent you shouldn't have spawned saves nothing.
Not a swarm generator. Five-plus agents is a precondition for Haiku, not a target.
Don't inflate a fan-out to unlock the cheap tier.
Quick reference
writes / runs / implements / designs / consequential → opus
judgment you'll act on, even with nothing written → opus
read-only, single agent → sonnet
>5 read-only agents in one batch, breadth sweep → haiku
unclear · underspecified · read feeding critical
unverified work → opus
sonnet/haiku came back thin → same task, one lane up
opus came back thin → sharpen the brief, same lane
"use the best model" (fable not named) → opus
token-heavy AND you can check the answer cheaply → grok (Cursor meter)
token-heavy but you cannot check it → opus
5h ≥ 80% or 7d ≥ 75%, reading fresh → shift checkable work to grok
quota reading stale / missing / NO DATA → route normally, say so
