Two frontier coding agents. One terminal. OpenAI built the bridge months ago — X just noticed.
On July 12, 2026, Shubham Saboo (@Saboo_Shubham_) posted that OpenAI dropped a Codex plugin for Claude Code — use Codex inside Claude for code reviews or delegated tasks. The tweet hit 63k+ views and linked openai/codex-plugin-cc.
Replies were immediate: "4 months ago… stop clickbaiting." "Fable 5 + gpt-5.5 medium is pretty good." "Two competing products are now teammates — who benefits?"
explainx.ai's read: not a launch, but the cleanest official pattern for the Codex vs Claude Code split developers already run — plan in Claude, execute or review in Codex — without bash duct tape.
TL;DR — what people are asking
| Question | Answer |
|---|---|
| New? | No — public repo, 28.2k★, v1.0.6 (Jul 8, 2026) |
| What it does | Claude Code → local Codex CLI for review + rescue |
| Install | Marketplace + /codex:setup — needs Node 18.18+, codex login |
| Key commands | /codex:review, /codex:adversarial-review, /codex:rescue, /codex:transfer |
| Reverse (Codex→Claude)? | Often blocked — one-way bridge |
| Best stack? | Fable 5 orchestrates · Codex/gpt-5.5 for cheap passes |
| Quota | Both Claude and Codex limits can burn |
Not "just dropped" — timeline vs hype
| Date | Event |
|---|---|
| Months prior | openai/codex-plugin-cc public · devs using /codex:review in production |
| Jul 8, 2026 | v1.0.6 release on GitHub |
| Jul 12, 2026 | @Saboo_Shubham_ viral repost · "just dropped" framing |
| Pushback | @michabbb — "4 months ago… embarrassing clickbait" |
explainx.ai standard: treat viral reposts as discovery events, not ship dates. The plugin matters because it is official, maintained, and documented — not because July 12 was day zero.
What you get — commands at a glance
From the official README:
| Command | Mode | Use when |
|---|---|---|
/codex:review | Read-only | Uncommitted diff or --base main branch review |
/codex:adversarial-review | Read-only, steerable | Challenge design — auth, races, rollback, caching |
/codex:rescue | Can edit | Debug, fix tests, continue prior Codex thread |
/codex:transfer | Handoff | Export Claude session → codex resume <id> |
/codex:status | Monitor | Background job progress |
/codex:result | Output | Final Codex output + session ID |
/codex:cancel | Control | Kill background job |
/codex:setup | Config | Auth check · optional review gate |
Background pattern (recommended for heavy reviews):
/codex:review --background
/codex:status
/codex:result
Natural language also works: "Ask Codex to redesign the database connection to be more resilient."
Install — copy-paste sequence
In Claude Code:
/plugin marketplace add openai/codex-plugin-cc
/plugin install codex@openai-codex
/reload-plugins
/codex:setup
Requirements:
- ChatGPT subscription (incl. Free) or OpenAI API key
- Node.js ≥ 18.18
- Global Codex CLI:
npm install -g @openai/codex - Auth:
!codex loginif/codex:setupfails
After install you should see slash commands plus the codex:codex-rescue subagent in /agents.
Config inheritance: plugin reads ~/.codex/config.toml and trusted project .codex/config.toml — same models and reasoning effort as standalone Codex. Example project override:
model = "gpt-5.4-mini"
model_reasoning_effort = "high"
Typical workflows
1. Ship gate — dual review
# Claude implements with Fable 5
/codex:review --base main
/codex:adversarial-review --base main challenge retry and cache invalidation assumptions
Matches Gokul Rajaram's split: Claude for planning, Codex for review and execution.
2. Rescue lane — cheap second implementer
/codex:rescue --model gpt-5.4-mini --effort medium investigate the flaky integration test
/codex:rescue --background fix the failing test with the smallest safe patch
spark maps to gpt-5.3-codex-spark for fast passes per README.
3. Session transfer — leave Claude, continue in Codex App/TUI
/codex:transfer
# → prints codex resume <session-id>
Uses Codex's external-agent session importer — same rules as importing Claude history in the Codex desktop app.
4. Theo-style routing in CLAUDE.md
explainx.ai already documents this in what is CLAUDE.md:
- Fable 5 / Opus — taste, plans, user-facing design
- gpt-5.5 via plugin — bulk implementation, migrations, data work
/codex:review— non-destructive quality pass/codex:adversarial-review— skeptical design review with custom focus text
No custom bash wrappers — native slash commands inherit Codex config.
One-way bridge — why Codex→Claude is hard
@iret77 (Jul 12 reply):
"you can simply ask Claude to call codex, grok and gemini as long as they are installed and authenticated… But when I try to call claude from codex, the tool call gets blocked hard."
explainx.ai read:
| Direction | Status |
|---|---|
| Claude Code → Codex | Official plugin + CLI delegation |
| Claude Code → Grok/Gemini CLI | Community pattern if binaries exist |
| Codex → Claude Code | Blocked / unsupported |
Anthropic and OpenAI both protect their harness — the plugin is distribution for Codex usage inside Anthropic's IDE, not neutral orchestration. ChatGPT Work vs Codex already showed OpenAI merging surfaces; this is the cross-vendor version of "stay in one UI, burn two quotas."
Who benefits — "two competitors as teammates"
@AgentOrToy asked who wins when Fable and Codex share a session.
| Party | Benefit |
|---|---|
| Builder | One workflow — plan/review split without repo hopping |
| OpenAI | Codex invocations from Claude-heavy users · GPT-5.6 Sol rescue tasks |
| Anthropic | Claude Code stays default shell · Fable still orchestrates |
| Both | Dual subscriptions normalized — matches "subscribe to both at ~$20" era |
CodeBucks reply: "Fable 5 + gpt 5.5 medium is pretty good combination" — cheap Codex passes under Fable planning.
Risk: limit whiplash on both sides if you chain background rescues + review gates during promo weeks.
Review gate — read the warning
/codex:setup --enable-review-gate
When enabled, a Stop hook runs targeted Codex review on Claude's response. Issues block stop until fixed — can loop Claude/Codex until quotas empty.
OpenAI README:
"The review gate can create a long-running Claude/Codex loop and may drain usage limits quickly."
Use only when actively monitoring — not overnight on Fable July 19 cliff anxiety runs.
vs rolling your own CLI calls
| Approach | Pros | Cons |
|---|---|---|
| codex-plugin-cc | Official · session transfer · background jobs · config inherit | Two billing pools |
Manual !codex | Flexible | No /codex:status · fragile prompts |
| claudex / proxy routing | OpenAI models as Claude API | Different architecture · ToS gray areas |
| Loop engineering only Claude | Single vendor simplicity | Miss Codex computer use / review strengths |
For enterprise, pair plugin use with DCG destructive-command guards on whichever agent touches prod.
FAQ from GitHub — quick answers
Same Codex account? Yes — local CLI auth shared.
Separate runtime? No — same machine, same checkout, same config.toml.
API key / custom base URL? Yes — set openai_base_url in Codex config.
Resume in Codex app? codex resume <session-id> from /codex:result.
Summary
openai/codex-plugin-cc is OpenAI's official Claude Code marketplace plugin — not new in July 2026, but the right integration if you already run Claude Code + Codex as a dual-agent stack. Install via marketplace commands, use /codex:review and /codex:rescue for read-only and implementation delegation, /codex:transfer to hop into Codex natively. Claude→Codex works; Codex→Claude mostly doesn't. Fable 5 + gpt-5.5 medium is the community sweet spot. Ignore "just dropped" hype — do enable the plugin if you pay for both harnesses anyway.
Not to be confused with: Agent Plugins, the cross-client open standard OpenAI announced with AWS, Cursor, GitHub, VS Code, and Vercel on August 6, 2026. That standard packages Agent Skills with MCP server configs for portability across Codex, ChatGPT, Cursor, GitHub Copilot, Kiro, and VS Code — a different, broader "plugin" concept than this single-client Claude Code marketplace plugin.
Related on explainx.ai
- Codex as a platform — OpenAI's open agent harness pitch, codex exec vs SDK vs app-server (Aug 19)
- Codex Multi-Agent V2 — delegation, GPT-5.5, and the Luna removal (Aug 16)
- Tibo vs Boris — Claude proxy ban + Work/Codex reset (Aug 9)
- Agent Plugins — OpenAI's new open standard (Aug 6, 2026)
- Codex vs Claude Code — developer verdict
- ChatGPT Work vs Codex — harness split same week
- CLAUDE.md routing — Fable + codex-plugin-cc mechanics
- Codex slash commands reference
- AI coding plugins ecosystem — OpenAI + Anthropic
- GPT-5.6 Sol in Claude Code via claudex
- Fable advisor + Sonnet executor patterns
- Loop engineering — when to stay single-agent
Sources: openai/codex-plugin-cc · @Saboo_Shubham_ July 12, 2026 · Codex v1.0.6 release
Plugin commands and model aliases follow the GitHub README as of July 13, 2026. Verify /plugin marketplace availability in your Claude Code build before production rollout.