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.
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.
Mobile automation engineers, AI/ML researchers building LLM-driven agents, RPA developers, and devs experimenting with LLM+device orchestration
I built a Skill layer that separates planning from execution:
- Planner: Claude Code / Codex (task decomposition, decision-making, replanning) - Orchestrator: Skill layer (state machine, retries/rollback, tool protocol) - Executor: phone GUI model (screen parsing + UI actions + cross-app execution)
Execution loop:
1. Goal in NL/template 2. Planner emits step plan + conditions + fallback strategy 3. Skill compiles into atomic actions (tap/type/swipe/wait/verify) 4. GUI executor runs on real/cloud phone, returns screenshots/state/structured output 5. Planner/orchestrator decide next step until success/fallback Potential use cases:
- recruiting outreach automation - multi-platform content distribution - social outreach workflows - lead extraction - competitor monitoring
Monitors X posts for Codex reset signals, but only matters if you pay for Codex.
Gives Claude its own machines—VM primitive for AI agents beats hogging your ports and RAM.
ASCII art plugin with zero utility beyond the joke itself.
Blog post comparing AI reverse engineering skills, not an actual tool or product.
Cross-agent skill sync is useful, but the audience is tiny right now.
Automated review gates that block code applies if a second agent finds critical issues.