OpenCode on Margrop Blog

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.

Couldn’t Get the GLM Coding Plan? Volcengine’s ¥9.9 Offer Can Drop to About ¥9.4 with an Invitation

Sat, 11 Jul 2026 03:20:00 +0800

Short answer

If the GLM Coding Plan is unavailable when you need it, refreshing the purchase page is not your only option. Volcengine Ark currently advertises the Coding Plan Lite subscription at ¥9.9 per month for the first two months. The same page lists a regular monthly price of ¥40, making the introductory price roughly 25% of the regular price, or “2.5 zhe” in Chinese discount terminology. The plan page also lists GLM-5.2 and says selected popular models receive a temporary four-times quota boost.

Read the fine print before buying: ¥9.9 is not a permanent price, the third month returns to the displayed ¥40 monthly rate, and Coding Plan quota is intended for supported coding tools rather than arbitrary general-purpose API traffic. This article and its screenshots were prepared on July 11, 2026. The official campaign page displayed an end date of August 7, 2026; always trust the live checkout page if the rules change.

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.

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.

Debugging Chinese Text Turning into Underscores in tmux + opencode: The Real Culprit Was client_utf8=0

Tue, 28 Apr 2026 18:40:00 +0800

Short version

This was not an opencode Chinese rendering bug, and it was not a broken terminal font. The tmux client had been detected as not supporting UTF-8. The decisive evidence was tmux display-message -p 'client_utf8=#{client_utf8}', which returned client_utf8=0. In that state, tmux replaces non-ASCII output with underscores, so every Chinese character inside the opencode TUI appeared as _.

This post documents a small but very typical terminal debugging session. On the same Mac, running opencode directly displayed Chinese text correctly. But after starting a tmux session first and then running opencode, all Chinese text became underscores.

This kind of problem is easy to misdiagnose. The first instinct is often to blame the font, the terminal emulator, the opencode version, a color theme, Nerd Font configuration, Unicode width handling, or a bug in the TUI framework. In this case, however, the key question was much narrower: does the current tmux client believe it can write UTF-8 back to the outer terminal?

To avoid exposing private environment details, all examples below are generalized. They do not include real hostnames, private addresses, session names, credentials, usernames, or project paths. The only things preserved are the technical facts needed to understand the failure and the fix.