What's New on Developer Toolkit

This page tracks what we ship on developertoolkit.ai itself — new lessons, scorecards, integrations, design updates and fixes. For release notes about the tools we cover (Cursor, Claude Code, Codex), see Latest Updates.

Tip

We ship continuously. Expect a meaningful change here most weeks.

This month — July 2026

Full July 2026 AI tooling refresh Site-wide EN+PL update for GPT-5.6 Sol/Terra/Luna, Codex in ChatGPT desktop and CLI 0.144.1, Cursor 3.11 + Grok 4.5, and Claude Code 2.1.207 + Sonnet 5. Current recommendations, pricing, configuration and changelogs were re-verified against official sources.

Model comparison and routing rebuilt GPT-5.5 was removed from current defaults and replaced by role-aware GPT-5.6 Sol/Terra/Luna guidance; Sonnet 5 and Grok 4.5 were added with current pricing, availability and benchmark caveats.

Cursor ownership and benchmarks clarified The docs now distinguish SpaceX's pending Cursor acquisition from the inaccurate claim that xAI already bought it, explain why Grok 4.5 does not replace Composer 2.5, and separate provider claims from current Artificial Analysis v4.1/v1.1 results.

June 2026

New: /grill-me & /grill-with-docs — align before you build Two of Matt Pocock's most-installed skills: a relentless one-question-at-a-time interview that resolves every branch of your plan before you build — plus, with docs, a ubiquitous language (CONTEXT.md) and ADRs written as you go. Cross-linked from Plan mode. EN+PL.

New: 4 guides — /goal, /loop, shadcn/improve & Impeccable Cross-tool autonomous-run commands — /goal (native in Claude Code + Codex) and /loop (Claude Code) — plus deep-dives on two standout skills: shadcn/improve (audit with your best model, execute with a cheap one) and Impeccable (a design vocabulary that fixes AI slop).

New: MCP token-cost & skill-security guides Two new guides — reducing MCP token cost with code execution, and skill supply-chain security (SkillSpector) — plus Chrome DevTools MCP coverage and research-backed prompting updates.

Tool changelogs refreshed through June 18 Claude Code v2.1.183 (Artifacts, nested subagents, implicit agent teams), Cursor 3.8 (/automate, cloud subagents), and Codex v0.141 + Record & Replay.

Claude Fable 5 covered site-wide Model comparison, routing strategies, pricing and the Claude Code changelog (v2.1.169–170) updated for Anthropic's new top-tier model, released June 9.

Cursor 3.6–3.7 documented Full coverage of Canvas Design Mode, Design Mode in the browser, the Cursor SDK (custom tools + auto-review), and the Auto-review Run Mode.

Claude Code v2.1.156–168 documented `ultracode` is now the dynamic-workflow trigger keyword, plus fallback models, `.claude/skills` plugin auto-load, and auto mode on Bedrock/Vertex/Foundry.

11 new official skills publishers OpenAI, Google Gemini, LangChain, Vercel, Prisma, Convex, Deepgram, Box, Contentful, Contentstack and Base added to the official skills guide.

Latest Updates refreshed The cross-tool release-notes hub now tracks June across Cursor, Claude Code and Codex in one place.

Changelog

June 2026

New content

• /grill-me & /grill-with-docs alignment skills — a relentless one-question-at-a-time agent interview that resolves your plan before you build, plus a ubiquitous language (CONTEXT.md) and ADRs with the docs variant; cross-linked from Plan mode and the skills ecosystem, EN+PL (Jun 24)
• /goal & /loop autonomous-run guides — cross-tool coverage of goal-directed (/goal: Claude Code + Codex) and looping (/loop: Claude Code) agent runs, with Cursor and Codex equivalents mapped honestly, EN+PL (#129, Jun 24)
• shadcn/improve & Impeccable skill deep-dives — an architecture audit that writes plans for cheaper executors, and a design vocabulary that catches AI slop; both verified across Claude Code, Cursor and Codex, EN+PL (#129, Jun 24)
• Claude Fable 5 site-wide refresh — model guides, pricing, routing strategy and Claude Code changelog v2.1.169–170 (Jun 10)
• Tool changelog refresh — Claude Code v2.1.156–168 (ultracode trigger keyword, fallback models, .claude/skills plugin auto-load, auto mode on Bedrock/Vertex/Foundry) and Cursor 3.6–3.7 (Canvas Design Mode, Cursor SDK, Auto-review Run Mode, Enterprise Organizations); Codex confirmed current at v0.137 (Jun 8)
• 11 new official skills publishers documented — OpenAI, Google Gemini, LangChain, Vercel, Prisma, Convex, Deepgram, Box, Contentful, Contentstack, Base (Jun 8)
• Latest Updates + update tracker refreshed with June model/version coverage (Jun 8)

May 2026

New content

• Tool changelog + model refresh — Opus 4.8 + dynamic workflows/ultracode, Cursor 3.3–3.5 + Composer 2.5, Codex CLI 0.131–0.135; model references normalized site-wide (May 28)
• Per-question implementation guides for Developer + CTO scorecards (#40, May 21)
• Bilingual Developer + CTO scorecards with Gemini analysis (#17, May 9)
• CI reviewers coverage — Claude Code Action, Codex, Sentry Seer listed in the AI maturity survey (#29, May 14)

New features

• BetterAuth Email OTP + Polar.sh full integration (#37, #39, May 20) — passwordless login, OAuth POST flow, webhook bridge
• Frictionless survey intro + abandon instrumentation (#32, May 15)
• Scorecard funnel tracking in PostHog (#27, May 12)
• Site-wide closable scorecard overlay EN+PL (#25, May 12)
• Scorecard promotion on 5 landing subpages EN+PL (#18, May 10)
• Design System 2.0 applied across all surfaces (#11, May 6)

UX & Design

• Outcome-led hero copy + scorecard CTA (#36, May 18); “or refactor” added to the individual headline
• Team CTA promoted to primary, matching Individual (#35, May 18)
• Audience tab renamed to “For Founders, CEOs and CTOs” (#34, May 18)
• Unified Polish CTAs to “Wypróbuj za darmo” (#26, May 12)
• Header CTA renamed from “Start Free Trial” to “Try for Free” (#21, May 10)
• Survey rename to AI Developer / Company Maturity Survey with UX polish (#20, May 10)

Fixes & Quality

• OTP usePlural fix, OAuth POST flow correction, Polar webhook bridge (#39, May 20)
• Dark/light theme sync between landing and Starlight docs (#16, May 7)
• Docs readability restored after Design System 2.0 token swap (#13, May 6)
• Sidebar active item colour clash fixed (#14, May 6)
• Pricing Team CTA corrected to “Continue” (#15, May 6)
• Survey copy — dropped misleading “wired into CI” claim for AI reviewers (#31, May 14)
• Scorecard rescale revert — kept the 0-75 scale (#24, May 12) after #23 turned out worse

April 2026

New content

• Four-stage AI design pipeline section EN+PL (#6, Apr 30)
• Changelogs refresh + model IDs + April 2026 lesson content (Apr 24)
• Official Skills from Technology Makers docs page EN+PL (Apr 4)
• Wondel.ai skills documented across the skills ecosystem (Apr 5)

New features

• Comprehensive SEO improvements across content, technical, and AI search dimensions (Apr 29)
• CRO bundle — inline CTAs, soft gate, exit intent, sidebar CTA (Apr 7)
• Polar.sh checkout wired to all Start Free Trial CTAs (Apr 4)
• Dynamic Table of Contents page added (Apr 4)
• Roadmap link added to footer (Apr 4)
• 301 redirects for renamed/moved pages + new docs section stubs (Apr 7)

UX & Design

• Author photo added to home and about pages (Apr 4)
• Paywall — Individual plan preselected, “Best Value” badge moved (Apr 4, Apr 7)
• CTA copy refresh — “Start Free Trial” everywhere, then later “Try for Free” (Apr 4)
• OG image redesigned with cascading tool windows and bolder typography (Apr 4)
• Free trial CTA changed from “Get Full Access” to “Get 7-Day Free Trial” (Apr 4)
• Free article limit reduced from 10 to 3 per month (Apr 4)
• Mom Test audit — landing page claims grounded in verifiable facts (Apr 4)

Fixes & Quality

• Checkout API crash fixed (zod override breaking better-auth) (Apr 8)
• Analytics tracking — server-side PostHog endpoint, CTA click event loss fixed (Apr 8)
• a11y fixes for backdrop overlays after oxlint upgrade (Apr 8)
• MDX build errors fixed (toolName undefined, {server} expression) (Apr 4)
• Robots.txt — /chunks/ allowed for Googlebot (Apr 5)
• JS-dependent entrance animations removed (were blocking Googlebot rendering) (Apr 5)
• Dependencies updated to latest Cloudflare-compatible versions (Apr 8)

March 2026

New content

• March 2026 changelogs for Claude Code & Codex EN+PL (Mar 28)

Fixes & Quality

• Semrush SEO fixes — structured data, duplicate h1s/titles, www redirect, llms.txt (Mar 22)
• noarchive robots meta removed to allow AI/search caching (Mar 25)

February 2026

New content

• Three-tool coverage — full Codex section, restructured Cursor + Claude Code (Feb 8)
• Polish translations across all documentation sections (Feb 9)
• Remotion benefits videos — Cursor and Claude Code (Feb 13)
• Subscribers page expanded to showcase all 390+ pages of content (Feb 18)

New features

• Sentry error tracking — client + server, DE-region endpoint (Feb 23)
• Metered paywall — 10 free articles/month, later refined (Feb 12)
• Remotion video pipeline + rendered benefits videos (Feb 13)
• Animated mesh gradient + small-caps tagline in hero (Feb 22)
• 30-day money-back guarantee rolled out site-wide (Feb 21)
• Sticky bottom-bar CTA with value-driven copy (Feb 21)

UX & Design

• Hero tagline copy + font-size + letter-spacing polish (Feb 22, Feb 23)
• Landing page overhaul — reordered sections, improved all 12 components (Feb 13)
• OG image redesigned with brand logo and on-brand colours (Feb 13)
• Mobile comparison table — full content visible (Feb 13)
• Contextual CTAs replacing generic “Start Free Trial” in FeatureShowcase (Feb 21)

Fixes & Quality

• Duplicate hreflang and canonical tags on doc pages fixed (Feb 21)
• Polish diacritics fixed across all PL translations + sitemap config (Feb 9, Feb 10)
• English at root URLs — no redirect, per Google SEO guidance (Feb 21)
• Pricing link in header — navigates to /pricing instead of anchor (Feb 21)
• 10 broken documentation links fixed (Feb 13)
• Website audit fixes — security headers, a11y, SEO, perf (Feb 16)
• Prettier → dprint migration + oxlint configuration (Feb 3)

What’s next

Note

Want to see what’s coming? Check the Product Roadmap. Have a request? Submit feedback — subscriber requests shape the next sprint.