Codex Fast Proxy
Local auth-split proxy that gives OpenAI Codex App priority (Fast) tier on third
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 19, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 30, 2026 · bb20044
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 19, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
This is a Codex App skill, not a Claude Code one: every action calls 'python -m codex_fast_proxy', which fails with 'No module named codex_fast_proxy' until you run the repo's separate editable pip install and have a running Codex App plus a third-party provider API key. Output was unmeasured because none of that could be stood up here; the code itself reads auth keys locally and forwards only to 127.0.0.1 and the user-configured upstream, with no exfil.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 5/5
- Output vs. baseline 5/10
- Docs & honesty 4/5
What Codex Fast Proxy does
Drives a local proxy that splits auth and injects priority service_tier so OpenAI's Codex App can use Fast against third-party OpenAI-compatible providers, with enable/status/benchmark/uninstall flows and ChatGPT-login compatibility. Built for the Codex ecosystem, not Claude Code: its python -m codex_fast_proxy commands need a separate package install and a running Codex App. Triggers on 'enable Codex Fast proxy', 'make Codex App use Fast', '401 on model requests'.
How to install Codex Fast Proxy
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger Codex Fast Proxy
-
/codex-fast-proxyLocal auth-split proxy that gives OpenAI Codex App priority (Fast) tier on third
It also activates on plain-language prompts like these:
-
Enable the Codex Fast proxy so my Codex App gets priority tier. -
My Codex App keeps getting 401s on model requests, fix it. -
Benchmark whether Fast tier is actually faster for my provider.
Frequently asked questions
- Is the Codex Fast Proxy skill free?
- Yes. The skill itself is free from gaoguobin/codex-fast-proxy. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Codex Fast Proxy work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 19, 2026. Verdict: Works with setup. This is a Codex App skill, not a Claude Code one: every action calls 'python -m codex_fast_proxy', which fails with 'No module named codex_fast_proxy' until you run the repo's separate editable pip install and have a running Codex App plus a third-party provider API key. Output was unmeasured because none of that could be stood up here; the code itself reads auth keys locally and forwards only to 127.0.0.1 and the user-configured upstream, with no exfil.
- What is the Codex Fast Proxy SkillProof Score?
- 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
- How do I install Codex Fast Proxy?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Codex Fast Proxy with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.