Claude Code gives more control. Codex reaches further.
Claude Code and Codex are both coding agents that run headless, in CI and on a schedule. They differ in reach and in control. Codex spreads one agent across the CLI, IDE extension, desktop app, cloud tasks and Slack and Linear hand-offs. Claude Code starts in the terminal and documents 33 hook events against Codex's 12. AI Developer Toolkit teaches all three tools side by side: 400+ guides and 100+ recipes, each showing when it was last updated.
$59.99 once for 12 months of access. Nothing renews on its own. 30-day refund on a first purchase.
- Compare data, updated
- 2026-10-16
- Claude Code 2.1.283
- 2026-09-26
- Codex 0.157.1
- 2026-09-26
- List prices captured
- 2026-09-26
Which one fits how you work?
Tick the lines that are true for you. Each one is a verdict line from the toolkit’s compare data, checked 2026‑10‑16.
Pick Claude Code if
Terminal-first: you review the result
Pick Codex if
Multi-surface: one agent across CLI, IDE, desktop and cloud
Station by station.
The jobs a coding-agent workflow has to do, with what each tool names for them. The note beside each station says whether the difference should change your choice.
Intent
Project instructions, skills, plan mode
Same shape Both read a project instruction file, with skills and plan mode. Claude Code reads CLAUDE.md (and by default AGENTS.md only when there is no CLAUDE.md, v2.1.277+); Codex reads AGENTS.md, and /init creates one.
Claude Code
-
CLAUDE.md; by default readsAGENTS.mdonly when there is noCLAUDE.md(v2.1.277+), and the/configProject instructions setting loads both - Skills in
.claude/skills/; bundled/code-review,/batch,/simplify - Plan mode:
/plan, Shift+Tab,--permission-mode plan
Claude Code 2.1.283, 2026-09-26
Codex
-
AGENTS.md(/initcreates one) - Skills:
/skills,.agents/skills/ - Plan:
/plan
Codex 0.157.1, 2026-09-26
Harness
Permissions and approvals, sandbox, MCP, hooks, organisation policy
Differs Both have an OS sandbox, approval controls and an organisation policy layer. Claude Code documents 33 hook events against Codex's 12, with five handler types; Codex hooks run only after you trust them.
Claude Code
- Permission modes: Manual (
default),acceptEdits,plan,auto,dontAsk,bypassPermissions; interactive sessions start in auto mode from v2.1.283,claude -pin Manual (auto mode there only on third-party providers or with telemetry off, from v2.1.285) - Sandboxed Bash: macOS Seatbelt, Linux and WSL2 bubblewrap
- Hooks: 33 events;
command,http,mcp_tool,promptandagenthandlers - MCP client:
claude mcp add(--scope projectwrites.mcp.json); runs as an MCP server withclaude mcp serve -
Readdeny rules in.claude/settings.json, for exampleRead(./.env) - Organisation policy: managed settings (
availableModels,permissions.disableAutoMode,deniedModels; v2.1.283)
Claude Code 2.1.283, 2026-09-26
Codex
- Approval policy (
-a on-requestor-a never) plus automatic review (--approve-for-me); starts inon-request - OS sandbox:
--sandbox read-only,workspace-write,danger-full-access; permission profiles (beta) - Hooks: 12 events; need persisted trust before they run
- MCP client:
codex mcp add,config.toml; does not run as an MCP server (removed in 0.154.0) - File access: a permission profile with a
denyfilesystem rule (beta);--sandboxalone restricts writes, not reads - Organisation policy:
requirements.toml(allow_managed_hooks_only,permission_profile,mcp_servers)
Codex 0.157.1, 2026-09-26
Loop
Stop conditions, /goal, /loop, scheduled runs, headless
Differs Both have /goal. Claude Code judges it with a separate evaluator model each turn and bundles /loop; Codex has no /loop in 0.162.1 (checked 2026-10-12), so use /goal or CI. Both run headless and on a schedule, but Claude Code Routines run in the cloud and Codex automations run locally in the desktop app. Claude Code can also serve as an MCP server; Codex removed that in 0.154.0.
Claude Code
-
/goal, judged by a separate evaluator model each turn -
/loopbundled skill (alias/proactive) - Scheduled runs: Routines in the cloud (
/schedule, research preview) - Headless:
claude -p;--output-format jsonorstream-json;--json-schema
Claude Code 2.1.283, 2026-09-26
Codex
-
/goal(featuregoals, stable) - No
/loopin Codex 0.162.1 (slash-command enum, binary strings) or the developer-commands reference (checked 2026-10-12); use/goalor CI Loop command guide, Codex 0.162.1, 2026-10-12 - Scheduled runs: automations run locally in the desktop app, which must be open and the machine awake Background and cloud agents guide, 2026-09-26
- Headless:
codex exec(aliase);--json(JSONL events);--output-schema FILE;-o FILE
Codex 0.157.1, 2026-09-26
Graph
Subagents, worktrees, background sessions
Differs Both have subagents, worktrees and background sessions (--worktree and --bg in Claude Code; --worktree, /subagents and the codex agents command center in Codex), but the loop lives in different places. Claude Code starts in the terminal and runs the same session in the IDE, desktop and web; Codex spreads one agent across the CLI, IDE extension, desktop app and cloud tasks (experimental).
Claude Code
- Subagents: built-in Explore, Plan and general-purpose; custom ones in
.claude/agents/ - Worktrees:
--worktree [name](-w) - Background sessions:
--bg, thenclaude attach,logs,stop - Cloud: web sessions (
claude --cloud)
Claude Code 2.1.283, 2026-09-26
Codex
- Subagents:
/subagents; multi-agent on by default - Worktrees:
--worktreeflag or/worktree - Background sessions: the
codex agentscommand center - Cloud: Codex cloud (
codex cloud, experimental)
Codex 0.157.1, 2026-09-26
Verification
Diff review, review agents, security review, checkpoints and rewind
Same shape Both review in the session (/code-review, /review) and from the shell or CI (claude ultrareview, codex review), and both have a security review. One caveat on rewind: Claude Code has checkpoints and /rewind, while Codex's Esc Esc backtracks the conversation but does not restore files (0.157.1).
Claude Code
- In the session:
/code-review(--fix,--comment) - From the shell or CI:
claude ultrareview(cloud, multi-agent); managed Code Review (Team and Enterprise; generally available per Anthropic) Code review automation guide, 2026-10-16 - Security review:
/security-review - Rewind: checkpoints and
/rewind(Esc Esc)
Claude Code 2.1.283, 2026-09-26
Codex
- In the session:
/review - From the shell or CI:
codex review,codex exec review - Security review:
@codex security review - Rewind: Esc Esc backtracks the conversation to an earlier message; it does not restore files (0.157.1). Use Git for file state
Codex 0.157.1, 2026-09-26
Release
CI and GitHub Actions, repo-event triggers, pull-request routing
Differs Both have a GitHub Action. Codex reviews on a mention (@codex review, GitHub and GitLab) without a separate workflow file and takes work from Slack and Linear. Claude Code reviews through its Action or managed Code Review and takes Slack through Claude Tag (Team and Enterprise).
Claude Code
- GitHub Actions and review on the pull request:
anthropics/claude-code-action@v1 - Hand-offs: Slack (Claude Tag for Team and Enterprise); others through MCP
- Reviewer routing and approval: through your own CI and CODEOWNERS
- Start a cloud run from code: Routines with an API trigger (research preview)
Claude Code 2.1.283, 2026-09-26
Codex
- GitHub Actions:
openai/codex-action@v1 - Review on the pull request:
@codex reviewon GitHub and GitLab, on a mention and without a separate workflow file - Hand-offs: Slack (
@ChatGPT, with Cloud delegation to a Codex Cloud task) and Linear (@Codex) Codex docs, 2026-10-12 - Reviewer routing and approval: through your own CI and CODEOWNERS
- Start a cloud run from code:
codex cloud(experimental)
Codex 0.157.1, 2026-09-26
Read a gap as a gap in what we read. A line that says “not found in the docs” means we could not source it on that date.
- Drawing
- Claude Code vs Codex
- Source
- The compare data, 2026‑10‑16. Each cell above names the page and the day it was read.
Models and what they cost.
Claude Code is included in Claude Pro at $20/month, Max 5x at $100 and Max 20x at $200. Codex is included in ChatGPT Plus ($20/month), Pro ($100, $200 or $500) and Business ($20 per user per month billed annually), and in Edu and Enterprise (OpenAI, read 2026-10-12); the 5x and 20x Plus-usage ratios of Pro at $100 and $200 come from a secondary source (TechCrunch, 2026-04-09).
| US list prices, 2026‑09‑26 | Claude Code | Codex |
|---|---|---|
| Models | Default Claude Opus 5.5 (v2.1.280+, on both release channels on 2026-10-17: stable v2.1.292, latest v2.1.302). Claude Fable 5.1 by hand with /model fable; Claude Sonnet 5.5 and Claude Haiku 5.5 when cost dominates (the haiku alias needs v2.1.293, latest channel only on 2026-10-17). Switch mid-session with /model | Default GPT-6.1 Sol (since CLI 0.159.1, 2026-09-29, at low effort); GPT-6 Astra chosen by hand for the hardest work; GPT-6 Sol and GPT-6 Luna in the picker; GPT-5.6 Sol, Terra and Luna still selectable. Switch with /model |
| Context window | 1M tokens on Claude Opus 5.5, Fable 5.1, Sonnet 5.5 and Haiku 5.5 | 272K by default in Codex, up to 872K (GPT-6.1 Sol, GPT-6 Astra, Sol and Luna) |
| Entry plan | $20/month Claude ProOr $17/month billed annually ($200 up front); Claude Code included | $20/month ChatGPT PlusCodex included (OpenAI pricing page, read 2026-10-12) |
| Middle plan | $100/month Claude Max 5xClaude Code; five times Pro usage | $100/month ChatGPT Pro (5x Plus)Codex; 5x Plus usage on Codex (secondary source: TechCrunch, 2026-04-09). Price: OpenAI, read 2026-10-12 |
| Top individual plan | $200/month Claude Max 20xClaude Code; twenty times Pro usage | $200/month ChatGPT Pro (20x Plus)Codex; 20x Plus usage on Codex (secondary source: TechCrunch, 2026-04-09). Price: OpenAI, read 2026-10-12. OpenAI also lists a $500 Pro tier |
| Team seat | Team Standard $25/seat monthly ($20 annual); Team Premium $125/seat monthly ($100 annual); Enterprise $20/seat/month billed annually, plus usage at API rates | ChatGPT Business $20/user/month billed annually ($25 billed monthly, 2+ users), with Codex included; Edu and Enterprise include Codex, price on contact (OpenAI, read 2026-10-12) |
Questions before you choose.
Something else? Write to support@developertoolkit.ai.
Is Codex included in a ChatGPT plan?
Yes. Codex is included in ChatGPT Plus, Pro, Business, Edu and Enterprise rather than sold separately. ChatGPT Plus is $20 a month, Pro is $100, $200 or $500, and Business is $20 per user per month billed annually (OpenAI, read 2026-10-12); Pro at $100 gives 5x Plus usage on Codex and Pro at $200 gives 20x (secondary source, 2026-04-09). When you reach the included limits, Codex offers credits and usage-limit resets.
Can both run without a human present?
Yes. Claude Code runs claude -p and Codex runs codex exec; both return machine-readable output (--output-format json and --json-schema in Claude Code, --json and --output-schema in Codex), both have a GitHub Action, and both run scheduled work (Routines, Automations). One caveat: Codex hooks need persisted trust before they run, which a fresh CI runner lacks.
Which has better goal-directed runs?
Both have /goal. Claude Code runs a separate evaluator model each turn. In Codex, goals is a stable feature and the agent doing the work audits its own goal. Codex has no /loop in 0.162.1 (checked 2026-10-12); Claude Code bundles /loop.
How do their safety controls differ?
Claude Code has six permission modes (Manual, acceptEdits, plan, auto, dontAsk, bypassPermissions) and 33 hook events. Codex pairs an approval policy (-a on-request or -a never) with an OS sandbox and 12 hook events that need persisted trust. Instruction files steer the model; hooks, sandboxes and approval policies can block an action.
Other comparisons.
Each one gives a verdict first, then goes station by station.
Does this page answer your questions?
One tap, no sign-in.
What are you here for?
What is holding you back?
How does it read?
Thanks. If you left an email, Michał will reply.
Answering your questions?
One tap each. Close whenever you like.
no sign-in
Pick one. Learn the workflow once.
The guides cover Cursor, Claude Code and Codex side by side, in the same order, so a move to the other tool later costs you little.
$59.99 once for 12 months of access. Nothing renews on its own. 30-day refund on a first purchase.
Michał replies, not a bot. The address is used for this reply only.