Toronto, Ontario
Joined February 2017
Stop bookmarking a million admin pages, docs sites, homelab dashboards, and test builds across your Tailscale network. zeulewan.github.io/web-finde… Install WebFinder on each device you want listed. Recommended for individual setups: web-finder start --auto-publish. iOS, macOS, and CLI. MIT licensed.
53
My eng capstone project. See zeuldocs.com/projects/capsto… for more details.
56
Passenger seat prompting When someone tells you how to prompt (usually unwarranted). Promptlem Problem with your prompt Prompt fatigue When you're too tired to properly prompt and you start making promptlems. Often late at night, your "agentic engineering" turns into pure vibe coding. U stop reading the output and start telling it "try harder." Person prompting / people prompting When you prompt a human to do something. Prompt Pollution U got shit in ur prompt that's gonna mess it up. Similar to a promptlem. Prompt perfectionist Someone that focuses too hard on getting their prompt just right. Often they try to fix every typo. Prompt Pause U go eat dinner.
3
1
124
Professor prompt Recording a prof, transcribing it, telling the AI to make sense of it.
1
96
Prompt Pleading ur on a call with ur friend and he tells u what to prompt and u beg him to just write it out so you can copy and paste it. Prompt Charity He gives u the prompt with nothing in exchange
79
I got OpenClaw working with Claude Max subscriptions again! I’m enjoying using OpenClaw more than ever because it’s actually cheaper than ever. I have it using the official Claude Code backend now with a custom system prompt, so my regular Max tokens work with it. Super easy to install but may be buggy rn. github.com/zeulewan/glueclaw Background: Anthropic changed their billing, which made API based use a lot more expensive. That’s all good, they’re rolling out Mythos, which likely needs a lot more compute, but I found that OpenClaw wouldn’t work through a custom system prompt even though other things still would. What I found out: By binary searching the OpenClaw system prompt and scrubbing out mentions of OpenClaw, I was able to get it working again. Technical info: It spawns the real claude CLI as a subprocess with --system-prompt and --output-format stream-json and translates OpenClaw's gateway tools through the MCP loopback bridge. The system prompt is scrubbed of Anthropic's detection triggers and response tokens like HEARTBEAT_OK are translated back so the gateway still works. It creates a model provider called glueclaw and three models: glueclaw-opus, glueclaw-sonnet, and glueclaw-haiku. PRs welcome. @steipete @openclaw If you want to integrate this upstream pls do. MIT licensed. Note: This project uses only official, documented Claude Code CLI flags. No reverse engineering, no credential extraction, and no API spoofing. I don’t believe this is against the TOS, but I’d love for Anthropic to clarify the policy here and let us know whether OpenClaw through the official Claude tooling is all good.
1
1
1
522