Cross-Harness Model Routing
Route agent work by capability axis: use the model with the strongest taste and judgment to plan, judge, and orchestrate; use Codex for well-specified execution, computer use, and UI verification when it is the better substrate.
Trigger
Use this workflow when:
- A Claude Code workflow or subagent needs work that Codex handles better.
- A task can be split into taste/judgment and mechanical execution.
- A high-taste model should not spend tokens on bulk edits, migrations, or repeated verification.
- User-facing UI, copy, or API design needs a stronger taste pass than the executor can provide.
- End-to-end agent PRs are producing too many branches that get closed after review.
Core rule
Do not pick one model for the whole run. Split the run by role.
| Role | Route |
|---|---|
| Taste, judgment, task decomposition, plan review | Fable/Opus-class Claude model, or the best current equivalent |
| User-facing UI, copy, API design | Taste model or explicit human review before shipping |
| Bulk implementation, migrations, data transforms | Codex via a self-contained codex exec prompt when the spec is clear |
| Computer use and UI/UX verification | Codex/computer-use route with browser or desktop receipts |
| Independent review | A second model or harness, preferably a different family |
Cost is a tie-breaker, not the primary objective. For work that ships, correctness and taste outrank cheapness.
Operating pattern
- The strong orchestrator reads the spec and writes a self-contained work packet.
- If the work is mechanical or verification-heavy, the orchestrator spawns a thin wrapper/subagent.
- The wrapper calls Codex CLI (
codex execorcodex review) with the packet. - Codex returns a patch, review, or verification receipt, not vague status.
- The orchestrator judges the output against acceptance criteria.
- If the output misses the bar, rerun or escalate instead of accepting mediocre work.
Thin wrapper contract
The wrapper is not the worker. It writes the prompt, calls Codex through the shell, and returns the result.
The prompt should include:
- repo path and branch
- files or subsystems in scope
- constraints and out-of-scope boundaries
- expected output format
- validation commands
- sandbox mode
- what evidence to return
Use read-only Codex runs for investigation and analysis. Use write-capable runs only when a patch or commit is intended. Always return receipts: commands run, files changed, screenshots or URLs for UI verification, and any failures.
Kevin stack defaults
Default to Codex for computer use, UI verification, and well-specified implementation when available. Default to Fable/Opus-class Claude models for plan review, implementation review, user-facing taste, API design, and copy. User-facing surfaces need a taste model or a human review gate.
Treat exact model names as dated defaults, not constants. Availability, pricing, and model quality change; the durable invariant is the split between judgment, execution, and verification.
Source snapshot
Theo's July 2026 CLAUDE.md example ranked models by cost, intelligence, and taste, then routed work accordingly. The table was an operator ranking, not a universal benchmark.
| Model | Cost | Intelligence | Taste |
|---|---|---|---|
| gpt-5.5 | 9 | 8 | 5 |
| sonnet-5 | 5 | 5 | 7 |
| opus-4.8 | 4 | 7 | 8 |
| fable-5 | 2 | 9 | 9 |
The useful procedure from the example:
- Bulk/mechanical work goes to GPT/Codex when it is effectively cheap.
- User-facing UI, copy, and API design need taste >= 7.
- Plans and implementations should be reviewed by a high-taste model; a second independent perspective is useful.
- When a workflow can only select Claude models directly, use a thin Claude wrapper to call
codex exec. - If the cheap run misses the bar, rerun or escalate.
Kevin's observation after adopting this workflow: Codex is still materially better for computer use, UI/UX verification, and efficient execution of well-specified work; routing that way reduced discarded end-to-end agent PRs from roughly half to zero in a day. Source: User, 2026-07-06
Failure modes
- Delegating vague work to a cheap executor produces bad PRs.
- Letting a wrapper summarize without receipts hides failures.
- Making cost primary ships mediocre work.
- Spending a taste model on mechanical chores burns scarce tokens.
- Using one model family to judge itself creates correlated blind spots.
Relationship to other pages
Borrowed Intelligence (Drain It into Plans) banks judgment into plans. This workflow drains judgment into live delegation packets. Claude Code Dynamic Workflows supplies the subagent/workflow dispatch layer. Cross-Agent Harness Portability keeps instructions, skills, and receipts portable so delegation does not drift per agent.
Timeline
- 2026-07-06 | Created from Theo's CLAUDE.md routing section and Kevin's Codex/Fable operating note. Durable rule: high-taste model orchestrates and judges; Codex executes and verifies well-specified work where it is stronger. Source: User-provided screenshot and X/@theo, 2026-07-06