cd /news/artificial-intelligence/theo-s-approach-to-running-gpt-5-5-a… · home topics artificial-intelligence article
[ARTICLE · art-55645] src=gist.github.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Theo's approach to running GPT-5.5 as a Claude Code subagent

Theo Browne published a guide for running GPT-5.5 as a subagent within Claude Code workflows, ranking models by cost, intelligence, and taste. The approach uses GPT-5.5 for bulk mechanical work via the Codex CLI, while reserving Claude models for user-facing tasks requiring higher taste scores. Browne provides detailed configuration instructions for integrating GPT-5.5 into Claude workflows, including wrapper agents and parallel execution with worktree isolation.

read2 min views11 publishedJul 7, 2026

(stolen from Theo Browne) Rankings, higher = better. Cost reflects what I actually pay (OpenAI is near-free for me due to a deal), not list price. Intelligence is how hard a problem you can hand the model unsupervised. Taste covers UI/UX, code quality, API design, and copy.

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

How to apply:

  • These are defaults, not limits. You have standing permission to override them: if a cheaper model's output doesn't meet the bar, rerun or redo the work with a smarter model without asking. Judge the output, not the price tag. Escalating costs less than shipping mediocre work.
  • Cost is a tie-breaker only; when axes conflict for anything that ships, intelligence > taste > cost.
  • Don't let cost prevent you from using the right model for the job. Instead, take advantage of cheaper options to get more information and try things before moving the work to a more expensive option.
- Bulk/mechanical work (clear-spec implementation, data analysis, migrations): gpt-5.5 — it's effectively free.
- Anything user-facing (UI, copy, API design) needs taste ≥ 7.
  • Reviews of plans/implementations: fable-5 or opus-4.8, optionally gpt-5.5 as an extra independent perspective.
  • Never use Haiku.
  • Mechanics: gpt-5.5 is only reachable through the Codex CLI — codex exec

/codex review

(my ~/.codex/config.toml defaults to gpt-5.5). Use the codex-implementation, codex-review, and codex-computer-use skills; for work they don't cover (investigation, data analysis), runcodex exec -s read-only

directly with a self-contained prompt. - Claude models (sonnet-5, opus-4.8, fable-5) run via the Agent/Workflow model parameter. Using gpt-5.5 inside workflows and subagents (the model parameter only takes Claude models, so use a wrapper):

  • Spawn a thin Claude wrapper agent with

model: 'sonnet', effort: 'low' whose prompt instructs it to write a self-contained codex prompt, runcodex exec

via Bash, and return the report (useschema

on the wrapper to get structured output back). - Always label these agents with a

`gpt-5.5:`

prefix, e.g.`{label: 'gpt-5.5:review-auth'}`

— the workflow UI shows the wrapper's Claude model, so the label is the only indication the real worker is gpt-5.5. - Codex runs can exceed Bash's 10-minute timeout: pass an explicit timeout, or run in the background and poll for the report file.

  • Parallel gpt-5.5 implementation agents must use isolation: 'worktree'

so codex edits don't collide in the shared checkout. - Workflow token budgets only count Claude tokens; codex work is free and invisible to

budget.spent() .

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @theo browne 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/theo-s-approach-to-r…] indexed:0 read:2min 2026-07-07 ·