Codex Reset Watchdog – a Skill for watching codex quota reset signals
Monitors X posts for Codex reset signals, but only matters if you pay for Codex.
Codex skill for preparing Foodpanda fruit carts and weekly email reminders
Codex skill automates Foodpanda cart building, but stops before checkout.
Foodpanda users in Pakistan wanting recurring orders
Selenium scripts · Playwright automation · iherb-CLI
Monitors X posts for Codex reset signals, but only matters if you pay for Codex.
Browser automation MCP for one Indian grocer; interesting proof-of-concept, zero production use case.
Shows how SKILL.md progressive disclosure can keep an LLM's context focused while turning routine RE tasks into repeatable playbooks — valuable thinking for anyone juggling analysts-in-the-loop workflows. Clever writeup and sensible environment notes (FLARE‑VM + VM isolation), but it stops at concept: no packaged skill repo, runnable examples, or tooling to actually drop into your lab, so it reads like research notes rather than a usable project.
Playwright automation lets AI agents order from Wolt, Bolt integration stubbed.
Splitting planner (Claude/Codex) from an orchestrator/skill layer that handles retries, rollback and stateful sessions is the project's best idea — it directly targets the brittleness of long LLM GUI workflows. The repo gives practical bits (CLI, install script, direct coordinate tap mode and unified JSON outputs), but it's early and niche: useful if you're building LLM-controlled phone automation, less interesting for general automation folks.
Gives Claude its own machines—VM primitive for AI agents beats hogging your ports and RAM.