Sign in

Mark Phelps

@markphelps.github.io
159 followers 379 following 143 posts

Built flipt.io. Now backend at @replicate. Previously helped build and scale GHCR @github . Father, Husband, beginner skateboarder. Aspiring vibe coder

PostsRepliesMedia
Mark Phelps @markphelps.github.io · 17/04/2026
Before AI: I moved slow, but I knew every line. Now: I move fast, and I'm auditing things I didn't write. Both ways are exhausting.
000
Mark Phelps @markphelps.github.io · 13/04/2026
Also added: - signed CLI for ops (summary, approve/reject, feedback, retention) - feedback memory so corrections sharpen future labeling - Skill file for Hermes to ping me twice daily reports
000
Mark Phelps @markphelps.github.io · 13/04/2026
You can just do things. Built a self-hosted cora.computer for email: - auto-triages into custom labels w/ AI - marks processed as read, uncertain → Needs Review - queues archive proposals for approval Runs on Cloudflare Workers + D1 + AI Gateway (Gemma 4)
100
Mark Phelps @markphelps.github.io · 06/04/2026
Use Google's latest OSS model Gemma-4 in Hermes or OpenClaw via @cloudflare workers AI It's seriously impressive and noticeably faster than Kimi in my testing
Post image
000
Mark Phelps @markphelps.github.io · 07/03/2026
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: markphelps.me/posts/building-llm-po…
000
Mark Phelps @markphelps.github.io · 25/02/2026
deepwiki is so good ask questions about a codebase in natural language no clone, no boot up, fast response with sources 🧑‍🍳😘
000
Mark Phelps @markphelps.github.io · 24/02/2026
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.
000
Mark Phelps @markphelps.github.io · 21/02/2026
Look how cute this lil dude is. This is much easier than building mobile apps ngl
Post image
000
Mark Phelps @markphelps.github.io · 21/02/2026
Me and Claude cooking this morning.. Who knew building Chrome extensions was this fun
Post imagePost image
010
Mark Phelps @markphelps.github.io · 20/02/2026
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
000
Mark Phelps @markphelps.github.io · 20/02/2026
vibe coded a chrome extension that explains PR changes as you scroll through them near-realtime what a time to be alive
Post image
000
Mark Phelps @markphelps.github.io · 20/02/2026
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: markphelps.me/posts/running-ai-agen…
000
Mark Phelps @markphelps.github.io · 19/02/2026
he’s great! doesn’t know about cue or dagger which is a plus. he spells certain words wrong tho.. like ‘organised’ smh
220
Mark Phelps @markphelps.github.io · 19/02/2026
cc @georgemac.bsky.social
110
Mark Phelps @markphelps.github.io · 19/02/2026
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
Post image
100
Mark Phelps @markphelps.github.io · 14/02/2026
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 openvault.agentty.sh We're cooked gang
010
Mark Phelps @markphelps.github.io · 09/02/2026
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.
Post image
000
Mark Phelps @markphelps.github.io · 08/02/2026
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.
000
Mark Phelps @markphelps.github.io · 08/02/2026
Built with: 🛠️ NextJS 🗄️ Supabase 🎨 Shadcn 🤖 Claude Code Opus 4.6 Shipped faster than I expected. The scaffolding does most of the work.
110
Mark Phelps @markphelps.github.io · 08/02/2026
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
Post image
100
Mark Phelps @markphelps.github.io · 08/02/2026
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.
100
Mark Phelps @markphelps.github.io · 08/02/2026
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 🧵
Post image
101
Mark Phelps @markphelps.github.io · 02/02/2026
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
000
Mark Phelps @markphelps.github.io · 02/02/2026
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...
100
Mark Phelps @markphelps.github.io · 02/02/2026
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.
110
Mark Phelps @markphelps.github.io · 01/02/2026
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?
010
Mark Phelps @markphelps.github.io · 30/01/2026
i think our jobs are safe for a little while longer..
Post image
010
Mark Phelps @markphelps.github.io · 25/01/2026
Now I just gotta find the time to start writing new posts...
000
Mark Phelps @markphelps.github.io · 25/01/2026
Spent a few hours yesterday bringing my old blog back to life: 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
100
Mark Phelps @markphelps.github.io · 09/01/2026
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!
Post image
000
Mark Phelps @markphelps.github.io · 07/01/2026
@Experian is impossible to reach when your account gets hacked. Their AI blocks you from any human help. Anyone dealt with this? WDYD?
000
Mark Phelps @markphelps.github.io · 06/01/2026
I don't and well never understand Nix and I dont care who knows it!
000
Mark Phelps @markphelps.github.io · 04/01/2026
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?
000
Mark Phelps @markphelps.github.io · 04/01/2026
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.
000
Mark Phelps @markphelps.github.io · 02/01/2026
Are we already at the point where foundational models have become commodities?
000
Mark Phelps @markphelps.github.io · 02/01/2026
I want this page as an API yourgpt.ai/tools/openai-and-other-l… Does this exist? Up to date LLM model prices/context limits/etc info as JSON
010
Mark Phelps @markphelps.github.io · 02/01/2026
Man i do miss those 2x usage limits today.. come on Anthropic please extend until most people go back to work on Jan 5
000
Mark Phelps @markphelps.github.io · 31/12/2025
What are you building with AI in 2026? Drop your best tips below 👇
000
Mark Phelps @markphelps.github.io · 31/12/2025
Finally, ABC - Always Be Clearing context. Compaction is the devil. If you've documented your plans and have a task tracker like Beads, you can nuke context whenever you want - this is the secret to cleaner code and sharper design.
100
Mark Phelps @markphelps.github.io · 31/12/2025
models are getting so good that less is more. you don't need a 2,000 line CLAUDE.md - quality drops after a certain point due to context limits. every so often ask Claude to trim its own CLAUDE.md file
100
Mark Phelps @markphelps.github.io · 31/12/2025
create subplans for large feature work before touching any code. this one for Claude Code is a game-changer: github.com/obra/superpowers Add a task tracking system like github.com/steveyegge/beads to track bugs, future enhancements, etc. You can now ship like a team of 5+
100
Mark Phelps @markphelps.github.io · 31/12/2025
use mobbin or dribbble to steal visual inspiration. drop screenshots in a 'design/influence' folder. then let your agent extract a design system - colors, icons, spacing, animations, the works. this lives right next to your PRD as the visual source of truth
100
Mark Phelps @markphelps.github.io · 31/12/2025
always start with a PRD and reference it in your CLAUDE.md/AGENTS.md the PRD is the source of truth when everything gets messy update it continuously as you learn what works Claude (web) is surprisingly good at creating these with the right prompt
100
Mark Phelps @markphelps.github.io · 31/12/2025
don't abstract too early-resist extracting components from a single screen until you're certain they'll be reused (atoms like buttons are the exception)
100
Mark Phelps @markphelps.github.io · 31/12/2025
Here's everything I've learned while 'vibe coding' react native iOS apps this year (most of this applies to any code, not just RN/mobile):
110
Mark Phelps @markphelps.github.io · 25/12/2025
calling it now: 2026 is the year of brutalist apps
Post image
000
Mark Phelps @markphelps.github.io · 23/12/2025
Gemini 2.5 Flash is absurdly fast and honestly holds its own against the bigger Gemini models.. at least for UI/design work. What are your thoughts chat?
000
Mark Phelps @markphelps.github.io · 22/12/2025
ask your ai agent to recommend 2-3 pre-commit hooks for your current project this + husky = vibe coding bliss
000
Mark Phelps @markphelps.github.io · 22/12/2025
CodexBar by @steipete is super nice. - works with Codex, Claude Code and Gemini - open source: github.com/steipete/CodexBar this feels like the future, AI helping us build polished little apps that do one thing really well.
Post image
000
Mark Phelps @markphelps.github.io · 21/12/2025
Me when Claude starts recommending these for new projects: - Go - Cloudflare Pages - Replicate API
Post image
000