AI CODING WORKSPACE

Build with Claude and Codex, then catch more bugs.

Q: How much is Winskel Pro?

US$20/month, or US$180/year (US$15/month billed annually), plus applicable tax. Annual billing saves US$60/year. Eligible accounts can start a 14 day free trial with a card; it renews automatically unless cancelled.

Q: How does the free year of Pro work?

The first 100 eligible Winskel users who create more than 5 qualifying projects can receive one year of Pro free. Eligibility begins at the sixth qualifying project and requires a server-confirmed grant. No payment card is required. The promotion is coming soon; progress and claiming are not available yet.

Q: Will I be charged after my free Pro year?

No. No card required. No automatic charge. Provider limits still apply. After the free year, your account returns to Free unless you choose a paid plan.

Q: Do Claude Code and Codex limits still apply?

Yes. Winskel Pro does not remove Anthropic or OpenAI usage limits.

Q: What can I use today?

The free Mac beta includes both agents, Project Memory, manual Second Opinion, standard debugging, Orchestrate, changes and recorded checks, and Deep Debug in beta with 10 uses a month. Automatic handoffs and Pro quality features are coming soon.

Q: Do I need both subscriptions?

No. Connect either supported coding agent, or both for cross-agent reviews. Sign in to the coding tools on your Mac. Provider limits and charges apply.

Q: What context is shared?

A short project brief: relevant decisions and work records, not every past conversation or shared private context windows. Agent-suggested facts need your approval.

Q: Can I correct or remove a saved decision?

Yes. In Settings, Context and memory, correct a decision or choose Forget. Project Memory stays Free; Pro Verified Project Learning is coming soon.

Q: Are reviews and fixes automatic?

Today you request Second Opinion and select fixes for the original builder. Manual review remains Free. Pro Auto Review and Auto Fix + Recheck are coming soon.

Q: What is the difference between Standard Debug and Deep Debug?

Standard Debug: read, search, edit and test. Deep Debug: a structured workflow to reproduce, investigate, repair and recheck, in beta.

Use the subscriptions you already pay for. Keep your work, project context, reviews and checks in one place.

Download for MacBook a demo

Current Beta · Free · Apple Silicon, macOS 12 or later

kickoffSaved cart

Illustrative sample · Deep Debug is in beta.

Built by a team from

Logos show where our team studied and worked. They don't imply endorsement.

Your agents don’t know what the other just did.

Without Winskel

Claude Code

Authentication updated

auth.ts · session.ts · login.tsx

Session refresh still needs work.

HANDOFF.md Writing the handoff…

Codex

I’ll inspect the project first.

Read 7 filesSearch authenticationCheck package.json

With Winskel One project. Ready to review.

Context and memory

What Winskel keeps about a project and gives to Claude Code and Codex. It works on its own: say a standing decision in chat, like “Remember that this project uses pnpm” or “Actually, use npm instead”, and Winskel keeps or updates it. Here you can check, correct, forget or limit what each agent gets.

Projectkickoff

Add a fact, like: Tests run with npm testKeep

What agents get in this project (2)

Use pnpm for this project.
You said this. Saved by you · Available to both agentsCorrectForgetClaude CodeCodex
Auth uses refresh tokens.
You said this. Saved by you · Available to both agentsCorrectForgetClaude CodeCodex

Diagnostics

Sample project. Relevant context only.

Know what actually ran before you trust “done”.

See what changed, what passed and what was never checked.

Sample project. Browser and email not checked.

Available today · Second Opinion

Catch what one agent missed.

Build with Claude Code. Ask Codex to check it. Or the other way around.

Areset.tssrc/signup/+7 -0

lines 10-16 · resetPassword

10+export async function resetPassword(email: string, token: string, password: string) {

11+ const stored = await db.resetTokens.first({ email });

12+ if (!stored || stored.expiresAt < Date.now()) return { ok: false };

13+ if (token !== stored.token) return { ok: false };

14+ await db.players.update({ email }, { password: await hash(password) });

15+ return { ok: true };

16+}

Mreset.tssrc/signup/+1 -0

lines 12-17 · resetPassword

1212 if (!stored || stored.expiresAt < Date.now()) return { ok: false };

1313 if (token !== stored.token) return { ok: false };

1414 await db.players.update({ email }, { password: await hash(password) });

15+ await db.resetTokens.delete({ email });

1516 return { ok: true };

1617}

Claude Code · Worked 1m · 2 reads, 2 edits, 1 check

Tests passed on the result (9b2f71c).

Open ReviewSecond Opinion

CodexGPT-6.1 Sol·Working00:00

Codex has started; nothing reported yet.

Codex found 1 issue, 1 that blocks the request.

HighReset token can be reusedsrc/signup/reset.ts, line 15The token is not invalidated after a successful password reset.

Fix selected issues (1)Sent to Claude Code, which built this. No new review starts by itself.

Claude CodeSonnet 5.5·Working00:00

Claude Code has started; nothing reported yet.

Claude Code · Worked 1m · 1 read, 2 edits, 1 check

Tests passed on the result (4c1e9a2).

Open ReviewSecond Opinion

Sample project.

See how reviews and checks work

Deep Debug Beta

Find the bug. Check the fix.

Reproduce the problem, fix the cause, then rerun the tests that failed.

I reopened my cart, but the total is broken. Please fix it.

Claude CodeFound the bug

Reproduce the bug

Two tests fail when the saved cart is loaded.

Find the cause

Check how the cart loads saved quantities.

src/store.jsInspecting

Looking for the cause…

Check the fix

Run those same tests after the change.

Did the fix work?

Same tests	Before fix	After fix
Saved items restored	× Failed	Not run yet
Cart total restored	× Failed	Not run yet

Waiting for the fix.

The original failures must pass after the change.

This example checks tests, without opening the app.

Recorded development example. Deep Debug: Beta.

Standard Debug

Free · Available today

Read Search Edit Test

Save a rule once. Both agents get it.

Claude Code and Codex receive your saved project rules before they start a task.

Project Memory

Context and memory

Projectkickoff

Add a fact, like: Tests run with npm testKeep

What agents get in this project (1)

Run tests before finishing.
You said this. For this projectCorrectForgetClaude CodeCodex

Diagnostics

Saved once Included before both agents’ tasks

Codex·Before next task

Receives the saved rule before starting.

Claude Code·Before next task

Receives the saved rule before starting.

Sample project. Saved rules are included before each agent’s task.

Use the subscriptions you already pay for.

Connect either one, or both.

Supported coding plans required. Provider limits apply. See setup requirements →

Pro · Available today

Let Winskel do more of the checking for you.

Unlimited Deep Debug

Use Deep Debug whenever a hard bug shows up. Included in Pro today (Beta).

Catch problems automatically

Auto Review · Coming soon

Turn found problems into checked fixes

Auto Fix + Check Again · Coming soon

Know when the code still needs work

JEV · Coming soon

Check what the app actually does

Test My App · Coming soon

Don’t solve the same bug twice

Project Learning · Coming soon

Set up your workflow once

Custom Workflows · Coming soon

Manual reviews and Project Memory stay Free.

Try Winskel free.

Free

Available today

Use Claude Code and Codex together.

$0/month

Free stays free.

Download for Mac

Free beta. No card required.

Deep Debug Beta

10 Deep Debug uses / month

Core workspace

Claude Code and Codex
Project Memory
Second Opinion
Changes + checks
Standard coding + debugging
Basic Orchestrate

Pro

Available today

Deep Debug without a Winskel monthly cap.

MonthlyYearly

US$20/mo

Billed monthly

Start a 14 day free trial

Card required. Then US$20/month plus tax. Renews unless cancelled.

Unlimited Deep Debug

Use Deep Debug whenever a hard bug shows up.

Planned Pro features · Coming soon

Catch problems automaticallyAuto Review · Coming soon
Turn found problems into checked fixesAuto Fix + Check Again · Coming soon
Know when the code still needs workJEV · Coming soon
Check what the app actually doesTest My App · Coming soon
Don’t solve the same bug twiceProject Learning · Coming soon
Set up your workflow onceCustom Workflows · Coming soon

One issue per Deep Debug use. Normal debugging and manual reviews don’t count.

Plan details and the beta reward →

Startup programs

AWS Activate
Microsoft for Startups
Notion for Startups
MongoDB for Startups

Questions

How much is Winskel Pro?

US$20/month, or US$180/year (US$15/month billed annually), plus applicable tax. Annual billing saves US$60/year. Eligible accounts can start a 14 day free trial with a card; it renews automatically unless cancelled.

Is Winskel Free staying free?

Yes. Winskel has a Free plan.

How does the free year of Pro work?

The first 100 eligible Winskel users who create more than 5 qualifying projects can receive one year of Pro free. Eligibility begins at the sixth qualifying project and requires a server-confirmed grant. No payment card is required. The promotion is coming soon; progress and claiming are not available yet.

Will I be charged after my free Pro year?

No. No card required. No automatic charge. Provider limits still apply. After the free year, your account returns to Free unless you choose a paid plan.

Do Claude Code and Codex limits still apply?

Yes. Winskel Pro does not remove Anthropic or OpenAI usage limits.

What can I use today?

The free Mac beta includes both agents, Project Memory, manual Second Opinion, standard debugging, Orchestrate, changes and recorded checks, and Deep Debug in beta with 10 uses a month. Automatic handoffs and Pro quality features are coming soon.

Do I need both subscriptions?

No. Connect either supported coding agent, or both for cross-agent reviews. Sign in to the coding tools on your Mac. Provider limits and charges apply.

What context is shared?

A short project brief: relevant decisions and work records, not every past conversation or shared private context windows. Agent-suggested facts need your approval.

Can I correct or remove a saved decision?

Yes. In Settings, Context and memory, correct a decision or choose Forget. Project Memory stays Free; Pro Verified Project Learning is coming soon.

Are reviews and fixes automatic?

Today you request Second Opinion and select fixes for the original builder. Manual review remains Free. Pro Auto Review and Auto Fix + Recheck are coming soon.

What is the difference between Standard Debug and Deep Debug?

Standard Debug: read, search, edit and test. Deep Debug: a structured workflow to reproduce, investigate, repair and recheck, in beta.

How many Deep Debug uses are included in Free?

10 Deep Debug uses a month. Normal debugging and manual reviews do not count.

What counts as one Deep Debug use?

One issue, including its investigation, bounded repairs and rechecks. A separate issue starts another use.

Does Pro include unlimited Claude or Codex usage?

No. Your provider subscriptions, usage limits and charges still apply. Pro removes only Winskel’s monthly Deep Debug cap.

What is JEV?

A planned extra quality model that helps decide whether a result needs more work. Pro feature · Coming soon.

What can Test My App check?

Coming soon. Supported journeys are not approved yet; production, mobile devices and third-party coverage are not promised.

Does Deep Debug guarantee bug-free code?

No. Inspect what passed and what remains unverified. Tests and reviews can miss problems.

Is Pro available?

Pro is available at US$20/month, or US$180/year (US$15/month billed annually), plus applicable tax. Eligible accounts can start a 14 day trial with a card, then renew automatically unless cancelled. Pro removes Winskel's monthly Deep Debug cap. The Free allowance is 10 Deep Debug uses / month. The six quality automation features remain coming soon and are not included until released. Provider usage limits still apply.

Build it. Debug it. Winskel

Download for Mac

Use your existing eligible Claude Code or Codex subscription. Provider usage limits still apply.Current Beta · Free · Apple Silicon, macOS 12 or later

Questions? Join us on Discord.

Winskel is independent. It is not made by, partnered with or endorsed by Anthropic or OpenAI.