Codex

Ben Tossell cancelled Superhuman and built a custom email client using Codex. It mirrors Superhuman's UX patterns but is fully customisable, runs on Gmail CLI, and is agent-native. The core AI logic is minimal: reading labels/archives and updating Gmail filters.

A structured /goal prompt template for AI coding agents (Codex, Claude Code, Hermes) that prevents scope creep, ranks uncertainties before acting, and closes completion loops. Key sections: GOAL (single measurable outcome), CONSTRAINTS, PLAN (understand-first), DONE WHEN (verifiable state), VERIFY (tests + rollback), STOP RULES (halt on ambiguity, surface ranked proposals not open questions).

Claude Code's /goal and Codex's /goal commands implement a completion-contract pattern: a working agent loops until a separate evaluator confirms a stated condition is met, judged only from evidence surfaced in the conversation. The post argues this punishes vague PM requirements faster than traditional development, raising the bar from 'write enough detail an engineer understands' to 'define done clearly enough an agent can keep trying and a harness can inspect proof.' Includes a practical goal template and anti-patterns.

Nick Baumann describes a multi-device Codex setup where a Mac mini serves as an always-connected 'home' node and a MacBook becomes a 'satellite,' with mutual SSH and cross-device thread continuity giving him phone-initiated, 24/7 Codex access across all three devices.

Michael Guo notes that Chrome Browser and Hyperframe are both available as Codex plugins, making them straightforward to incorporate into AI creative workflows.

Jason Liu's workflow guide for getting maximum leverage from OpenAI Codex by treating it as a persistent work OS rather than a one-shot chat tool. Key primitives: durable pinned threads (Command-1 through Command-9), voice input for unedited thinking, steering to queue intent mid-execution, an Obsidian vault as shared agent memory, Heartbeats for recurring loops, and the side panel for artifact inspection and annotation.

Vijay Iyengar argues the default weekly 1:1 is structurally flawed because its fixed cadence decouples meetings from actual need. He proposes replacing most 1:1s with public-channel work, real-time escalation, written decision communication, ambient connection, and work-oriented feedback—while preserving 1:1s for onboarding (daily for 2-3 weeks), early-career reports, remote teams, on-demand requests, and peer-manager alignment.

Codex has matured from a coding assistant into a general work OS. Core patterns: durable pinned threads (Cmd+1–9 shortcuts), voice input for vague prompts, steering (mid-task interruption) vs. queuing (next-task scheduling), tool layers ($browser/$chrome/@computer), thread automations on a schedule, Goals with explicit verifiers (test suites, benchmarks), side panel for in-place artifact review, and shared memory via Obsidian vault with AGENTS.md routing rules.

An evolved meta-prompt instructs Codex to audit its own session history, Memories, and Chronicle over 30 days to identify repeated manual workflows and package them as skills, subagents, or automations — only creating the smallest useful artifact and skipping speculative or already-covered work.

Codex has gained self-management capabilities: it can create threads, search and organize them, pin important ones, and spin up git worktrees for parallel tasks — reducing the manual overhead of maintaining a multi-thread coding workflow.