Codex on Margrop Blog

Can You Still Buy a Coding Plan? A July 2026 Reality Check on Limits, Quotas, and Lockouts

Mon, 20 Jul 2026 09:00:00 +0800

Short answer: as of July 20, 2026, most mainstream AI coding plans are still purchasable. The confusing part is that “available to buy,” “available in my region,” and “available for heavy coding” are no longer the same statement. Some products have a live checkout but tight quotas; others are visible in marketing pages but not offered to every account; some individual coding experiences have been paused or reshaped during product transitions.

Superpowers 6: What Actually Changed, and Why Your Agent Got Harder to Fool

Mon, 13 Jul 2026 15:30:00 +0800

The short answer

If you already write code with Claude Code, OpenCode, or Codex, you have probably heard of Superpowers. It is not another “magic prompt.” It is a skill framework that makes your agent work by process — turning the habits of a good engineer (“think before you act”, “write the test before the code”, “collect evidence before fixing the bug”) into operating procedures the agent must follow.

From v6.0.0 to the latest v6.1.1, Superpowers shipped a dense run of upgrades: Subagent-Driven Development (SDD) lost half its reviewers but got stricter; plans gained a Global Constraints block and per-task Interfaces; the brainstorming companion got a one-time key; Codex can install from the marketplace; and Gemini CLI was dropped after Google EOLed it.

This article unpacks the wave, what you actually get, and why it makes your agent’s output steadier.

Four Hard Resets in One Weekend—and Two Cards: When Tokens Stop Being Scarce, What Are We Actually Missing?

Mon, 13 Jul 2026 07:00:00 +0800

The short version

Codex users spent the weekend inside a restaurant that would not stop refilling the buffet. There was one hard quota reset early Friday morning Beijing time, two more on Saturday, and another waiting on Monday morning. A bankable reset card also appeared. As Tibo celebrated Codex reaching six million active users, he previewed another card for everyone the following day.

At the same time, the five-hour limit was temporarily removed for Codex subscribers, leaving only the weekly limit. I also had a substantial pool of GLM-5.2 quota expiring on Sunday. The old problem was saving tokens. The new problem was stranger: how do I spend them on work that deserves them?

After a weekend that felt busy, surprising, and slightly absurd, my conclusion is simple: the scarce resource in the AI era may not be tokens. It may be worthwhile questions, distinctive ideas, and the ability to turn those ideas into reality quickly.

Stop Hunting for YOLO Flags: One Launcher for 6 AI Agent Tools

Mon, 06 Jul 2026 09:50:00 +0800

Short version

In AI Agent tools, yolo does not mean “the model is smarter.” It means “ask me fewer questions.” It reduces or skips approval prompts so the Agent can run more like an unattended automation script. The annoying part is that every tool names this differently. Codex exposes a dangerous approval-and-sandbox bypass. Claude Code has a dangerous permission-skip mode and a permission mode. Gemini CLI and Qwen Code use --approval-mode=yolo. OpenCode uses --auto plus permission rules. Aider uses --yes-always.

My recommendation is not to overwrite codex, claude, or gemini with risky aliases. Install an explicit agent-yolo launcher instead. When you really want high autonomy, type agent-yolo codex, agent-yolo claude, or agent-yolo gemini. This article provides Windows 11, Ubuntu 26.04, and macOS 26 scripts. They do not depend on third-party services, do not install missing Agent tools, and do not contain private addresses, full computer names, private domains, tokens, or keys.

Do Not Waste Your Codex Quota Before the Reset: Meet Codex Reset Radar

Sun, 24 May 2026 08:10:00 +0800

The short version

Codex resets have recently become more important to watch. Sometimes the reset is part of the normal usage cycle. Sometimes it is a compensation reset after an incident. Sometimes it follows a fix for abnormal limit consumption. For heavy Codex users, the painful part is not that the quota resets. The painful part is discovering that you still had useful weekly quota left, but you did not use it before the reset overwrote the old window.

Codex Reset Radar is a small public dashboard that turns scattered public signals into a practical warning: if a Codex quota reset window is likely or already open, it tells you to use your remaining weekly quota on valuable work before it expires.

This article discusses only public pages, public status signals, and public references. It does not include private accounts, tokens, internal systems, private network details, or personal usage data. Any discussion of quota, reset windows, and early warnings is a user-side workflow analysis, not an official statement about OpenAI billing, subscription policy, or service guarantees.

Your MCP Config Was Fine. The Server Died Before the Handshake.

Sat, 23 May 2026 06:10:00 +0800

The short version

The misleading part of this incident was the surface error. Codex reported that an MCP client could not initialize and that the MCP server handshake failed. That naturally pushes you toward MCP configuration, JSON-RPC initialization, plugin settings, authentication, network transport, or stale tool caches. But the root cause was lower than the MCP protocol: one local MCP server binary was killed by the macOS dynamic linker before it could answer the initialize request. The client only saw a closed connection. The useful evidence was in the server stderr: dyld: Symbol not found, pointing at a missing Swift Concurrency runtime symbol.

In other words, MCP did not really get a chance to fail. The server process died first.

This article walks through a real troubleshooting pattern around Codex, MCP clients, and MCP servers. The failure looked like a protocol startup problem, but the root cause lived in a native macOS binary and its Swift runtime compatibility.

All private details have been removed. This article does not include real internal addresses, usernames, session IDs, full local paths, tokens, private repository names, or business system names. Paths use placeholders such as ~, <USER_HOME>, <PLUGIN_DIR>, and <PROJECT>. Log snippets keep only the technical fields needed to explain the diagnosis.

Stop Letting Agents Guess UI: Installing and Using UI UX Pro Max the Right Way

Fri, 22 May 2026 22:50:00 +0800

The short version

UI UX Pro Max is not a magic prompt that suddenly gives an agent taste. It is a searchable UI/UX design intelligence Skill for AI coding assistants such as Claude Code, Codex, Cursor, Windsurf, Gemini, OpenCode, and similar tools. It packages product patterns, UI styles, color palettes, typography pairings, landing page structures, chart recommendations, UX guidelines, and stack-specific implementation advice into files and scripts that an agent can actually query.

The right way to use it is not to install it and keep asking for “a beautiful page.” The right way is to make the agent generate a design system first, then query UX, chart, web, or stack-specific guidance, and only then implement the page. That workflow reduces generic AI gradients, weak contrast, crowded mobile layouts, decorative dashboards, missing focus states, and many other common agent-generated UI problems.

This article uses only public references, a public repository, and a clean temporary verification directory. Commands, paths, project names, and examples are generic. No private addresses, credentials, internal project names, account names, or personal configuration are included. Screenshots are taken from public reference pages and sanitized verification work.

Upgrading PVE 8 to 9 Without Brute Force: Let an Agent Drive It, or Follow This Manual Checklist

Tue, 12 May 2026 19:00:00 +0800

Short version

Upgrading Proxmox VE 8 to 9 is not just copying a few commands. It is a major system upgrade from Debian Bookworm to Trixie, from PVE 8.4 to PVE 9.x, with kernel, storage, networking, Ceph, and HA behavior in the blast radius. The fastest practical path is to let Codex, Claude, OpenClaw, HermesAgent, or a similar Agent handle checks, command sequencing, logging, and post-upgrade verification. The human operator still needs to approve repository changes, package removals, configuration prompts, reboot timing, and recovery decisions. If you prefer doing everything by hand, the second half of this article gives a concrete manual checklist.

This article is for two groups of operators. The first group already uses Agents over SSH and wants a scoped one-sentence task for upgrading PVE. The second group prefers typing every command manually and wants a clear, ordered procedure with the main risk points called out.

All hostnames, addresses, repositories, tokens, and accounts in this article are placeholders. Replace values such as <PVE_NODE>, <BACKUP_TARGET>, and <ADMIN_CONSOLE> with your own environment. Before touching a production host, read the official Proxmox documentation and verify that your backups are restorable.

Codex 0.130 Removed /approvals? The Fix Is to Move Permissions to Startup Flags

Tue, 12 May 2026 18:50:00 +0800

The short version

If you upgraded to Codex 0.130.0 and noticed that the old /approvals habit no longer works, the practical fix is not to downgrade. Move the permission policy to launch time. Use --ask-for-approval to control when Codex asks, --sandbox to control what commands can touch, and reserve --dangerously-bypass-approvals-and-sandbox for environments that are already isolated outside Codex. The long flag can also be written directly as --yolo, which is easier to remember, easier to type, and more consistent with command habits from tools such as Gemini.

In other words, stop treating approval mode as an in-session toggle. Treat it as part of the way you start the agent.

This article only discusses public Codex CLI flags and generic workflows. It does not include real hostnames, internal addresses, usernames, tokens, private paths, or project names. Commands use placeholders such as <PROJECT> and <TASK>.

Ubuntu 26.04 Upgrade Guide: Let an Agent Do It, or Run It by Hand

Tue, 12 May 2026 07:30:00 +0800

The short version

Upgrading Ubuntu 22.04 or 24.04 to Ubuntu 26.04 is not about memorizing one command. It is about following the supported upgrade path. Ubuntu 22.04 LTS should not be jumped directly to Ubuntu 26.04 LTS. Upgrade 22.04 LTS to 24.04 LTS first, then move from 24.04 LTS to 26.04 LTS. As of 2026-05-12, Ubuntu 26.04 LTS has already been released, but the normal LTS-to-LTS upgrade prompt from 24.04 LTS to 26.04 LTS is typically enabled after the first point release. The official 26.04 schedule lists the 26.04.1 point release on 2026-07-09. Production systems should usually wait for the regular upgrade path; test systems can evaluate an early upgrade only with explicit risk acceptance.

If you already use agents such as Code, Claude, OpenClaw, HermesAgent, Codex, or OpenCode, this is a good task to delegate. But do not just say “upgrade Ubuntu.” Give the agent a bounded job: inspect first, back up, follow the supported path, keep logs, ask before risky choices, reboot, verify services, and report evidence. This article gives both a ready-to-copy agent prompt and a manual procedure.

All examples in this article are generic. No private hostnames, internal addresses, accounts, credentials, tokens, business system names, or personal paths are included. Replace placeholders such as <HOST>, <SERVICE>, and <BACKUP_DIR> with values from your own environment.

Small Models Make Agents Drift. Superpowers Gives Them Rails.

Thu, 07 May 2026 16:43:10 +0800

The short version

When an agent powered by a smaller or weaker model behaves unpredictably, the problem is not always solved by writing a longer prompt. Smaller models often struggle with long-horizon consistency, tool discipline, evidence tracking, and multi-step execution. Superpowers does not turn a weak model into a frontier model. What it does is more practical: it gives the agent an external engineering workflow made of reusable Skills, checkpoints, testing habits, debugging rules, review steps, and completion verification.

For agents such as OpenClaw, HermesAgent, Codex, Claude, Gemini, OpenCode, Droid, Cursor, and similar tools, Superpowers is best understood as an engineering-discipline layer. It makes the agent less dependent on improvisation and more likely to follow a repeatable process.

This article is about a very common failure mode in modern agent workflows: the model can talk fluently, but the agent does not behave reliably once the task becomes long, stateful, tool-heavy, or distributed across multiple agents.

The issue becomes more visible when using smaller domestic models, local models, quantized models, or cost-optimized models. They may answer normal questions well enough, but once they need to read a repository, follow a constraint, modify files, run tests, interpret logs, preserve privacy, and report only verified results, the instability becomes obvious.

All examples in this article are generic. No private hostnames, internal addresses, credentials, project names, or personal paths are included.

How to Prompt OpenClaw, HermesAgent, Codex, Claude, Gemini, OpenCode, and Droid to Write Articles and Publish WeChat Drafts

Tue, 05 May 2026 16:00:00 +0800

Short version

If you want an agent such as OpenClaw, HermesAgent, Codex, Claude, Gemini, OpenCode, or Droid to write an article, prepare a Hugo blog post, convert the Chinese version into WeChat-compatible HTML, preview it, fix layout issues, and create a WeChat Official Account draft, the prompt cannot simply say “write and publish an article.” A useful prompt must define the goal, source material, paths, account constraints, fixed-IP requirements, conversion steps, preview checks, failure recovery, privacy boundaries, and final verification evidence.

This post describes a reusable prompting pattern for article automation. It explains how to prepare the WeChat draft API, why a Linux machine with a fixed public IP is often required, how to tell an agent to try local API access first and then fall back to a fixed-egress host, how to use a Markdown-to-WeChat-HTML converter, and how to make the agent check for invisible white text, strange indentation, broken images, and accidental leaks before declaring the job done.

All examples are privacy-safe. They use placeholders rather than real secrets, private IP addresses, hostnames, repository URLs, tokens, cookies, or personal paths. Replace placeholders with your own values only in a protected runtime environment, never in a public article, public repository, or screenshot.

Using WoClaw to Solve Shared Memory for Multi-Agent Workflows: OpenClaw, Codex, Claude, and Gemini on the Same Table

Sun, 05 Apr 2026 20:10:00 +0800

What matters most in a multi-agent system is often not “which model is smarter”, but “which agent still remembers what happened five minutes ago”.

When I put OpenClaw, OpenAI Codex, Claude, and Gemini into the same workflow, the most painful problem was not raw answer quality. It was context fragmentation:

OpenClaw remembered scheduling decisions, Codex remembered implementation details, Claude remembered review conclusions, and Gemini remembered external references, but none of them knew what the others knew.
Each tool had its own session lifecycle, so yesterday’s discussion was often gone by tomorrow.
As soon as a project entered a multi-round, multi-tool stage, repeating the same background became more expensive than solving the problem itself.
Without a shared memory layer, the final result was not collaboration, but several partial answers that looked similar and still failed to line up.

This post is about how I used WoClaw to place all of those tools on the same shared memory layer, so they could stop talking past each other and start working from the same state.

To avoid leaking private information, all examples below are abstracted. They do not include real hostnames, account names, addresses, tokens, or internal project codes.

OpenAI GPT-5.4 Explained: Positioning, Capabilities, Cost, and Practical Adoption (As of 2026-03-06)

Fri, 06 Mar 2026 08:20:00 +0800

On March 5, 2026, OpenAI officially released GPT-5.4. The first question many people asked was simple: is this just another small point release, or is it a real shift in how much productive work the model can finish?

If you only look at the version number, 5.4 looks like the next iteration after 5.2 and 5.3. But once you line up the official launch notes, model docs, API capability matrix, and the ChatGPT-side product updates, the core value of GPT-5.4 is not “how many more parameters it has.” The real change is that it pulls three lines of capability into a much more usable center point:

Reasoning
Coding and engineering execution
Tool ecosystem coordination, including computer use