What Not to Ship, Susannah!
Trinny and Susannah never asked what you fancied wearing.
They opened the wardrobe, held up the worst offender and told you exactly why it had to go.
AI-built screens need the same treatment: sparkle emoji, tracked uppercase labels, 10px text and a gradient on everything.
Sinan Yorulmaz (@sinanyorulmazz) of Enmera has built that wardrobe raid as an open-source package, ai-design-check.
What goes in the bin bag?
It ships 95 design rules, and a checker with no dependencies and no API key tests 57 of them automatically.
It reads React, Vue, Svelte and plain HTML, plus SwiftUI and Jetpack Compose apps.
Every finding names the file, the line and the rule, like outline-none with no replacement focus ring.
The 38 rules a pattern can't judge are left for a human, or the agent, to eyeball.
Who does the makeover?
That's the job of an Agent Skill (a folder of instructions your coding agent loads when it needs them) for Claude Code, Cursor and Codex, installed with npx skills add enmerasoftware/ai-design-check.
Ask it to "fix the design of this screen" and it measures the gaps and radii, writes a four-line brief, then repairs things in order of harm, accessibility first.
It never deletes content to lower the count, so features, data and copy stay put.
On the repo's demo dashboard, that took 266 findings down to zero.
Can it stop a relapse?
Yes, wire it in as a Claude Code hook (a command that runs automatically after the agent edits a file).
{
"hooks": {
"PostToolUse": [{
"matcher": "Edit|Write|MultiEdit",
"hooks": [{
"type": "command",
"command": "npx -y @enmera/ai-design-check hook"
}]
}]
}
}
A clean file passes silently, and anything else goes straight back to the agent to fix.
In CI, --format github turns the same findings into pull request annotations.
Older projects can record today's findings as a baseline, so only new crimes get reported.
Kinda sweet.
👉 ai-design-check
Willy Wonka and the Pull Request Factory
Willy Wonka didn't stir every vat himself…
He built a factory and let the Oompa Loompas run it.
Most of us still run coding agents the other way round, one laptop and one session at a time, babysitting CI and review comments.
Darko Fabijan (@darkofabijan), CEO of SuperPlane, just shipped SuperPlane 1.0, an open-source software factory (a shared system that turns tickets into tested code changes) for teams.
What happens on the factory floor?
It reads the backlog and scores each task for clarity, complexity and verifiability before any agent touches it.
Approved tasks run in their own cloud environment, in parallel, with whichever model we pick.
Every change comes back with evidence, from passing checks to screenshots of the real UI, and failing CI or review comments send the agent back in until the PR is ready for a person.
The whole team shares one board showing what's running, what failed and what it cost.
Can we keep the factory in our own garden?
Yes, the engine is Apache 2.0 and installs on a single VM with Docker Compose.
VERSION=v1.0.0
REPO=https://github.com/superplanehq/superplane
TAR=superplane-single-host.tar.gz
curl -fsSL -o "$TAR" \
"$REPO/releases/download/$VERSION/$TAR"
tar -xzf "$TAR" && cd superplane
# up to 8 runners at once, 2 kept warm
SUPERPLANE_RUNNER_MAX_CAPACITY=8 \
SUPERPLANE_RUNNER_WARM_CAPACITY=2 \
./install.sh
Each concurrent runner wants 2 vCPUs and 8 GB of memory, so the factory is cheap to open but not to fully staff.
The team says 52% of the pull requests they merged last month went through SuperPlane, mostly work nobody would have got round to.
Hosted plans start at pay-as-you-go, and bringing our own model keys adds no token markup.
No golden ticket required… BOOM! xd
Just a bug in the backlog and a factory that does the tasting before we do.
👉 SuperPlane
📦 GitHub Agentic Workflows GA
Write your CI chores in Markdown, gh aw compile turns them into Actions YAML, and Copilot, Claude Code or Codex does the triage… read-only and sandboxed by default, so the agent can't merge its own homework.
📦 GitHub-Verified MCP Connectors
Connect Slack, Figma, Notion, Sentry, Linear and 21 more once, and they work across the Copilot app, CLI, VS Code and Mobile… no more pasting the same OAuth dance into five config files.
📦 Copilot in VS Code, Universe Edition
Cloud sessions that follow you from phone to desk, an Agent Host that keeps running after you close the window, and experimental computer use with /computer on… your standup can now start a PR.
📦 Copilot Server-to-Server Auth
GitHub Apps can now call the Copilot SDK on behalf of an org with no signed-in human, billed to the org… your bot finally gets its own badge instead of borrowing yours.
📦 Replit Cloud Agents
Anyone on a Pro or Enterprise team describes a change, and the agent clicks through it in a sandbox and opens a PR with a video attached… the marketing team now ships code, engineering still holds the merge button.
📦 Claude Code Blocks Stray Writes
permissions.blockWritesOutsideWorkingDirectories keeps Write and Edit inside your project in every mode, long sessions now compact past 200K tokens instead of asking for credits, and CLAUDE_CODE_DISABLE_ULTRATHINK exists for the brave.
📦 Codex 0.166
Keyboard-driven transcript search, GPT-6.1 Terra in the Vertex AI and Bedrock catalogs, and codex doctor --network-only… for when the real bug is the hotel Wi-Fi.
📦 Kiro Approve for Me
Kiro CLI 2.36 approves routine actions, blocks risky ones and asks when unsure, saved per workspace… goodbye to pressing Y four hundred times before lunch.
📦 Mistral Vibe 3.0.3
Skills now hot-reload mid-session, agent hooks land, and experimental tracking ties each PR or MR back to the session that made it… a receipt for every vibe.
📦 Etraveli Flight MCP
The engine behind Booking.com flights now lets Claude or ChatGPT search 550+ airlines and book through a hosted payment link… your agent still can't get you the window seat for free, though.
📦 Pipefy MCP Client and Server
Pipefy agents can call Slack and Salesforce, and Claude Code or Cursor can run Pipefy processes as tools… the approval workflow can now approve itself, with an audit trail.
Enjoyed this? Join The Agentic Rewind for a weekly look at AI agents and dev tooling that actually ships 👉 https://theagenticrewind.com/
Top comments (0)