Latest
GPT-6.1 Terra Computer Use API: Tested at About $0.01 per Task
In a 9-task browser test, GPT-6.1 Terra passed 104 of 108 runs at $0.010–0.016 a task, but it submitted forms twice until one dropdown instruction fixed it.
20 min
Developer Tools & Agents
Guides to AI coding agents and developer tools: CLI and IDE assistants, MCP servers, local models, agent configuration, and workflows that hold up in daily use.
- 59 articles
- Updated Nov 4, 2026
Qwen Usage Limits: What Each Limit Message Means and What Helps
Qwen Chat is free, but its daily, per-model and per-feature caps are unpublished. The limit message names the cap you hit; paid plans live as of Oct. 31, 2026.
15 min
Codex Could Not Start in VS Code: WSL, SSH, and Container Fixes
“The extension could not start its user interface” on Codex 26.1021.22027? Go back to 26.1007.21434. On WSL with VS Code 1.141.1, update VS Code instead.
22 min
DeepSeek Super Agent on GitHub: Setup, and Why Exit 3 Is Normal
dsh-superagent is a DeepSeek Harness plugin, not an app. It needs its own GitHub account, tmux on macOS or Linux and a model key. Exit 3 on first run is normal.
14 min
Codex Weekly Limit Reset: Find Your Time or Reset Now
Codex has no fixed reset day. Tibo's 28-day campaign has brought four global resets as of October 20, 2026; Settings → Usage shows whether one reached you.
22 min
MiniMax M3.1 Flash Size: 428B Params, 252 GB on Hugging Face
MiniMax M3.1 Flash has 428B parameters (23B active) and a 252.4 GB official download. “Flash” means 4-bit experts, not a smaller model than M3.
15 min
How to Install Gemini CLI (2026): Setup and Which Login Works
Install Gemini CLI 0.65.0 with npm and Node.js 20+. Personal Google sign-in stopped working June 18, 2026: use a paid API key, Vertex AI or Antigravity CLI.
21 min
Best Local Coding LLM for 16GB VRAM: gpt-oss, Qwen3.8, Gemma 4
For a 16GB VRAM GPU, start with gpt-oss-20b. Try Qwen3.8-27B only as a 3-bit file with a q8_0 cache, and use Gemma 4 12B when you need long context.
25 min
Antigravity Plan Mode Missing? It Returned as /plan in App 2.17
Antigravity's 2.0 app dropped the Planning/Fast picker on May 19, 2026. Use /plan in App v2.17.0+ or Shift+Tab in the CLI, and set plans to always need review.
12 min
Codex Asking for Phone Verification? Each Error and What to Do
Codex in the ChatGPT desktop app may require phone verification that email or an authenticator app can't replace. What each error means and the safe next step.
18 min
Codex account/read failed during TUI bootstrap: Fix by the Tail
Read the tail after “account/read failed:”. In most reports timed out or failed clears with a background-server restart; 401 needs a new sign-in on that host.
24 min
ChatGPT & Codex GPT-5.5 Model Not Found: Retired Oct 14, Fixes
ChatGPT "Model not found" since Oct 14 has no official cause: try a new chat or browser, then support. In Codex, gpt-5.5 retired; use gpt-6.1-sol.
20 min
Codex API Key vs Subscription: Which Costs Less, What You Lose
At OpenAI's 2,500 credits = $100 rate, Codex credit rates match API prices per token, so plan usage, cloud features, and models decide. As of Oct 10, 2026.
16 min
Codex Game Studio Plugin: Install, Use, and Pick the Right One
OpenAI's Game Studio plugin steers Codex toward 2D Phaser or 3D Three.js browser games. Unity, Godot, and Chromatic projects need a different plugin.
13 min
Best OpenClaw Skills to Install First (2026): Starter Packs by Workflow
Start with the skill that completes your recurring job: summarize for long source material, gog for Google Workspace, or github for repository status. Web research and browser work may already have the tools they need. Check what your agent can use before installing another skill.
13 min
ChatGPT Agent Local Files: Work, Codex, and Claude Code Access
A local path alone grants no access. Upload a selected document, use Work with approved local computer access, or open the checkout in local Codex or Claude Code. Then verify the actual file version and permitted actions.
16 min
ChatGPT Plus Codex Usage Limits and Credits: Is Codex Included?
Yes, Codex is included in ChatGPT Plus. OpenAI estimates 15–150 GPT-6 Sol messages per five hours, weekly limits may apply, and credits extend usage.
19 min
ChatGPT Pro Codex Limit: Check Usage and Reset (No 5-Hour Window)
Pro 100, 200 and 500 have no five-hour Codex limit, but an included allowance and weekly limits still apply. Settings → Usage shows what's left and the reset.
13 min
ChatGPT Scheduled Tasks: Context, Memory, Files, and Tools
A future task needs explicit instructions and accessible sources. Use an existing chat for ongoing work, treat Memory as supporting context, and give shared copies their own inputs and app access.
12 min
Codex CLI Token Cost: Estimate Daily API Spend Before a Long Run
For API-billed Codex CLI work, price ordinary input, cache reads, cache writes, and output separately. A planned day can then be compared with your budget before the next long task starts.
15 min
Multi-Agent Coding Workflow for Small Teams: Worktrees, Roles, Review Gates
Start with one implementer and a separate review pass. Add parallel writers only when their tasks have stable boundaries, and test their combined candidate before it reaches main.
14 min
OpenClaw + laozhang.ai Setup Guide: Configure and Verify Your Custom Provider
Add laozhang.ai as an OpenClaw custom provider using https://api.laozhang.ai/v1 and the openai-completions adapter, then select an accessible model. A configured entry is only the first step: the Gateway must resolve its API key, and the agent and session must actually use that route.
12 min
Codex /goal: What It Does, How to Use It, and Why It May Be Missing
Codex /goal keeps one objective attached to a chat so work can continue across turns. Set a clear finish line, use the documented lifecycle controls, and accept completion only when the requested evidence is present.
9 min
Codex Token Exchange Failed 403: Diagnose and Recover Sign-In
A Codex token-exchange 403 is a refused authentication request. The full error tells you whether to repair callback access, check the client’s network, renew stored credentials, or stop for an access restriction.
11 min