I got tired of reviewing PRs blind.
So I built Sherpa - a Chrome extension that explains GitHub PRs as you read them. On demand. Your code never leaves your machine.
New post on how it works:
https://markphelps.me/posts/building-llm-powered-code-review-sidebar/
deepwiki is so good
ask questions about a codebase in natural language
no clone, no boot up, fast response with sources
🧑🍳😘
Apple finally approved my FamilyControl prod permissions. Going to finally launch Stay on TestFlight this week.
Related, I migrated trystay.app to @Cloudflare with OpenNext in 5 mins from the Triangle Co.
Saves $40/month.
Post image
Look how cute this lil dude is. This is much easier than building mobile apps ngl
Post image
Post image
Me and Claude cooking this morning.. Who knew building Chrome extensions was this fun
Post image
Gave Sherpa a fresh coat of paint and now it's running on @Cloudflare Workers + Durable Objects so summaries stay synced across tabs and users in real-time
Post image
vibe coded a chrome extension that explains PR changes as you scroll through them
near-realtime
what a time to be alive
Adding devcontainer support to Flipt let me use --dangerously-skip-permissions with Claude Code.
Now the agent can run wild inside the container. Can't touch my host.
Mounted my skills in. Full control.
Wrote about why this matters:
https://markphelps.me/posts/running-ai-agents-in-devcontainers/
he’s great! doesn’t know about cue or dagger which is a plus. he spells certain words wrong tho.. like ‘organised’ smh
cc @georgemac.bsky.social
Post image
Show me your OpenClaw agents. Here's mine:
Hunter - Blog & social posts
Gilfoyle - Server maintenance 🤘
George - Flipt business. British, organised
David G - Workout planning & accountability
Dwight - Assistant to the regional manager. Coordinates them all
Codex 5.3 is scary good.. and fast.
Vibed this landing page using some frontend skills from skills.sh
Deployed to Cloudflare Workers using the Cloudflare Docs MCP server
https://openvault.agentty.sh/
We're cooked gang
Post image
OpenClaw Mission Control update: usage graphs
1.1M tokens across 4 agents in 6 days
main: ~500k 🐷
coding: ~200k
social: ~30k
blog: ~15k
Models:
opus-4-6: 45%
gpt-5.2-codex: 35%
MiniMax: 15%
Now I know exactly where my API budget goes.
The best part: seeing what the LLMs actually return.
- Tool calls with full payloads.
- Structured outputs.
- Token breakdowns per turn.
- Success/fail metrics.
You spend all day talking to agents. Never see what's under the hood.
Now you can.
Built with:
🛠️ NextJS
🗄️ Supabase
🎨 Shadcn
🤖 Claude Code Opus 4.6
Shipped faster than I expected. The scaffolding does most of the work.
Post image
Mission Control:
- Activity timeline - every message, tool call, cron job
- Calendar - 12 scheduled jobs, all tracked
- Full-text search across ALL conversations + transcripts
- Raw data panel - see exactly what the LLM saw
OpenClaw is great, but it's a black box.
You see the response. You don't see:
- What the LLM actually processed
- How many tokens per turn
- Which tools fired
- Success/failure rates
I wanted visibility. So I built it.
Post image
Everyone's building OpenClaw mission controls.
I built one too, but with a twist:
It shows you what OpenClaw hides—the raw LLM inputs, tool calls, token counts, everything.
A thread 🧵
If I'm struggling this much to get a setup I love, non-techies are gonna have a bad time
Or could just be a skill issue
First the clawdbot → openclaw transition
Then trying to get multiple agents talking to each other
People are selling openclaw setups to non-tech users as a service
It ain't ready for that...
I've installed and nuked clawdbot/openclaw like 4 times now. Local linux, then VPS. Each time something broke badly enough that nuking and starting over was the only option.
I'm building an MCP gateway in Rust 🦀
Instead of loading every tool upfront, your agent gets four meta-tools: search, inspect, call, list.
Progressive discovery. 50 tokens vs 18,000 for typical workflows.
Useful or solving a problem that doesn't exist?
Post image
i think our jobs are safe for a little while longer..
Now I just gotta find the time to start writing new posts...
Spent a few hours yesterday bringing my old blog back to life:
https://markphelps.me
Go/Hugo -> Astro
AWS S3 -> Cloudflare R2
Netlify -> Cloudflare Pages
Thumbnails conjured via Replicate API
I have been fully absorbed into the orange cloud
Post image
Opus is a beast at planning (and coding) but I still have it spawn parallel subagents using Sonnet 4.5 when possible because Sonnet also ships code like a machine.
Save on those rate limits!
@Experian is impossible to reach when your account gets hacked. Their AI blocks you from any human help. Anyone dealt with this? WDYD?
I don't and well never understand Nix and I dont care who knows it!
thinking about building a simple app that tracks car maintenance + deadlines (registration, inspection, insurance renewals).
i keep a spreadsheet (like a nerd) but never look at it until something's already overdue.
anyone actually solved this or is everyone just vibing?
One thing I've noticed over this holiday break:
I've been rapidly prototyping ideas with AI, then taking a full day to sit with them and decide if they're actually worth pursuing.
And since the code is AI-generated, killing bad ideas feels completely painless.
