Open to Backend and Mobile Engineering roles.

sky
Joined April 2018
Okpe Onoja retweeted
Played around with a left-to-right calendar swipe interaction in @expo , with a smooth, natural glide✨
3
7
293
Okpe Onoja retweeted
Been playing around with drag-and-drop reordering in @expo . The transitions are smooth, and the little haptic feedback as items switch places makes it feel so good✨
3
8
394
Okpe Onoja retweeted
Your personal website is the new resume
3
5
164
Okpe Onoja retweeted
Played around this card drag interactions on a calendar using @expo ✨
3
11
302
Okpe Onoja retweeted
One thing that worries me about using AI coding agents is how easy it is to accidentally share something sensitive. You could paste a terminal log, ask for help debugging, and unknowingly include an API key. That’s why I’m building Promptwall. I want to make it harder for developers to accidentally expose secrets while working with AI.
I'm building Promptwall, a local guard for agentic coding that catches API keys and sensitive data in your prompts to Claude Code, Codex and other AI agents, then blocks or redacts them.
1
3
3
244
Okpe Onoja retweeted
Played around with @X ’s slide-out drawer in @expo . Also added a solid/soft toggle that changes the calendar cards on the fly. Love how it turned out.
4
18
702
Okpe Onoja retweeted
Ever pasted a log into an AI coding agent without realizing it contained a live API key? That’s what I’m building Promptwall to prevent. It catches secrets in prompts, logs, and commands before they reach your agent.
I'm building Promptwall, a local guard for agentic coding that catches API keys and sensitive data in your prompts to Claude Code, Codex and other AI agents, then blocks or redacts them.
2
3
142
Okpe Onoja retweeted
CSM manages your AI coding sessions. Promptwall catches secrets in prompts, logs, and commands before they reach your agents. I’m exploring how both can work together to make agentic coding safer. Here’s a quick look.
I'm building Promptwall, a local guard for agentic coding that catches API keys and sensitive data in your prompts to Claude Code, Codex and other AI agents, then blocks or redacts them.
1
3
5
170
Okpe Onoja retweeted
A quick look at Promptwall. Paste a prompt containing a secret, and Promptwall catches it before it reaches your AI agent. Here’s a short demo.
I'm building Promptwall, a local guard for agentic coding that catches API keys and sensitive data in your prompts to Claude Code, Codex and other AI agents, then blocks or redacts them.
2
1
142
Okpe Onoja retweeted
Been working on making CSM a better place to manage all your coding agents and accounts, without the constant logging in and out.🚀 usecsm.xyz ✨
3
6
312
Okpe Onoja retweeted
I'm building Promptwall, a local guard for agentic coding that catches API keys and sensitive data in your prompts to Claude Code, Codex and other AI agents, then blocks or redacts them.
7
2
1
14
1,165
Okpe Onoja retweeted
Checkout: usecsm.xyz 🚀
Built CSM 🫡 A CLI for running multiple Claude Code, Codex, Gemini CLI & GitHub Copilot CLI accounts on one machine. Switch accounts without logging out, keep your session, and automatically fail over to another account when one hits its usage limit. Your tokens/cookies/Keychain secrets stay with the agents. CSM doesn’t store or copy them. Open source → github.com/onoja123/csm
2
108
Okpe Onoja retweeted
Happy to launch CSM 🚀 If you use Claude Code, Codex, Gemini CLI or Copilot CLI with more than one account, CSM lets you switch between them without logging out. Your session, conversation and context come with you. Pick up exactly where you stopped. usecsm.xyz Domain from @brimblehq btw✨
4
7
12
631
Okpe Onoja retweeted
1
2
85
Okpe Onoja retweeted
Skill issue iamthecode.xyz/ Claude on auto👀
Claude btw, just dey use am build....e too useless for design 😭😭😭
54
37
17
553
75,027
Okpe Onoja retweeted
CSM can also help you move beyond managing agents. Build Room coordinates agents across tasks, branches, testing and review, with your approval before changes are pushed. AutoFix connects to Sentry workflows to investigate errors, reproduce them in a sandbox, create fixes, verify them and prepare pull requests for review. From managing agents to getting work shipped.
1
1
1
83
Okpe Onoja retweeted
More than account switching. Skills Library: manage skills across supported agents and carry task requirements through handoffs. MCP carry: bring supported MCP configuration along when switching, without copying secrets. CSM Desktop: Mission Control tracks sessions across projects, while the macOS menu bar gives you a quick view of agent activity and approvals. Available as both a CLI and a desktop app.
2
1
1
103
Okpe Onoja retweeted
Your work shouldn’t be tied to one agent. With CSM, hand off tasks between Claude Code, Codex, Gemini and other supported agents. It carries a structured brief with your goal, progress, files changed, commands, Git state and next steps. You can also save checkpoints without stopping your agent, review what was captured, add notes, and pick up later. Switch agents. Keep the work moving. 🤝
1
1
134
Okpe Onoja retweeted
How it works: Each account gets its own profile, signed in once through the agent's own login. Run csm claude like normal. Hit a limit? Run csm next to continue on your next account with the same conversation. Or enable csm auto automatic and CSM handles confirmed usage limits for you, saving a checkpoint and resuming your work on the next ready account. No logout. No copy-paste. No guessing.
1
2
1
193