# Writing

> AI coding workflows, coding-agent field notes, and LLM reviews by AI Kai (hqman, @hqmank).

Tested AI coding workflows, coding-agent field notes, and honest LLM reviews for builders using Codex, Claude Code, Cursor, and agents.

- [Make AI Explanations Easier to Read with ASD-STE100](https://hqman.me/blog/asd-ste100-ai-explanations.md): Use Simplified Technical English to make AI explanations clearer: short sentences, consistent names, explicit actions, and a prompt you can copy.
- [Free Muse Spark 1.3 in Cline, With Chrome MCP on Your Existing Session](https://hqman.me/blog/cline-free-muse-spark-chrome-mcp.md): Cline lists Muse Spark 1.3 Contributor, DeepSeek V4.1 Flash, and GLM-5.3-Flash as free. I tested Spark with Chrome MCP on my logged-in browser.
- [Codex Stops at 4 Subagents. Raise multi_agent_v2 Concurrency](https://hqman.me/blog/codex-multi-agent-v2-parallel-subagents.md): Codex defaults to 4 concurrent subagents. This multi_agent_v2 config raises the session cap so you can run dozens in parallel. Start small to avoid 429s.
- [I Open-Sourced a PDF Invoice Skill for Coding Agents](https://hqman.me/blog/pdf-invoice-skill.md): I open-sourced a PDF invoice skill for coding agents. One prompt updates days, discount, fees, and the balance due on a generated PDF.
- [GPT-6 Astra Rebuilt This 3D Globe Dashboard](https://hqman.me/blog/gpt-6-astra-3d-globe-dashboard.md): I ran GPT-6 Astra on a static Three.js logistics dashboard. One prompt, a collapsed activity drawer, and a live demo at hqman.me/demo/gpt-6-astra-3d-globe.
- [Keep Using OpenAI Models in Cursor After November 12](https://hqman.me/blog/use-openai-models-in-cursor-after-november-12.md): Use CLIProxyAPI and Cloudflare Tunnel to keep OpenAI models in Cursor after the proposed November 12, 2026 cutoff, with setup and security caveats.
- [Codex Usage Reset August 30, 2026: Tibo on Longer Limits](https://hqman.me/blog/codex-usage-reset-token-optimization.md): The August 30, 2026 Codex usage reset comes with token fixes from OpenAI. Tibo says the same limits may last 10% to 50% longer.
- [Cursor After SpaceX: OpenAI Cuts Access While Anthropic Stays](https://hqman.me/blog/cursor-openai-anthropic-spacex-model-access.md): OpenAI plans to end Cursor's direct model access on November 12, while Anthropic says it will keep supporting Claude in Cursor.
- [Stop Reviewing Agent Code: Lauren Tan's System](https://hqman.me/blog/stop-reviewing-agent-code.md): Lauren Tan merged 1,000 PRs last month with agent auto-merge. Her 4-layer system: verification, feature maps, CI constraints, and guardrail accumulation.
- [Tencent Hy4 Preview: 770B MoE, 1M Context, Free](https://hqman.me/blog/hy4-preview-free-two-weeks.md): Tencent's Hy4 preview is an open-source 770B MoE model with a 1M-token context window. WorkBuddy and CodeBuddy offer it free for two weeks.
- [How to Build a Daily AI News Bot with Grok Bot](https://hqman.me/blog/grok-bot-daily-ai-news-assistant.md): Build a dedicated Grok Bot that automatically researches, filters, and delivers a high-signal AI news digest every morning as a clean HTML page.
- [Grok Build: Grok 4.6 Agent with Native Browser Use](https://hqman.me/blog/grok-build-grok-46-browser-use.md): Grok Build brings Grok 4.6 to the terminal with native Browser Use plugin support for web automation, testing, and full-stack coding workflows.
- [Ox Alpha Is a New GLM Model. GLM-5.3 Flash Is Still My Guess](https://hqman.me/blog/ox-alpha-glm.md): Ox Alpha GLM is a new Z.ai GLM iteration. I still guess GLM-5.3 Flash because this stealth model takes images and video, unlike GLM 5.2 in my tests.
- [Shopify's Claude Code Warning: AGENTS.md Support](https://hqman.me/blog/claude-code-agents-md-compatibility.md): Shopify CEO Tobi Lütke may ban Claude Code over AGENTS.md support. See how fragmented agent system prompts and skills affect Codex teams.
- [The Story Behind Codex Reset, According to Tibo](https://hqman.me/blog/codex-reset-tibo.md): Tibo Sottiaux says Codex Reset began as usage compensation after broken builds. He still controls the reset button.
- [Ox Alpha Rebuilt My 3D Globe Dashboard on OpenRouter](https://hqman.me/blog/ox-alpha-globe-test.md): I ran Ox Alpha in OpenCode on my 3D globe test. One prompt, a working Three.js page, and a live demo at hqman.me/demo/ox-alpha-3d-globe.
- [Grok Bot 0.18.0 Shipped with Runtime Source Maps](https://hqman.me/blog/grok-bot-runtime-source-maps.md): A source-map mistake exposed enough of Grok Bot 0.18.0 to reconstruct its runtime, prompts, tools, and model routing.
- [A Dual-Agent Coding Workflow with Codex and ChatGPT Pro](https://hqman.me/blog/codex-chatgpt-pro-workflow.md): Use Codex as project lead and independent verifier while ChatGPT Pro handles focused engineering tasks through a browser-based collaboration loop.
- [Codex Usage Will Reset Again. OpenAI Found the Drain.](https://hqman.me/blog/codex-usage-reset-rate-limit-fixes.md): OpenAI found several causes behind faster Codex usage drain and plans a full paid-user reset. Builders are already planning what to run next.
- [Cursor Origin: Code Hosting Built for AI Agents](https://hqman.me/blog/cursor-origin-ai-code-hosting.md): Cursor Origin combines Git hosting, review, collaboration, and agent-focused conflict handling in a beta platform designed for parallel coding agents.
- [How to Use DeepSeek Models in Codex](https://hqman.me/blog/deepseek-codex-integration.md): Configure Codex to use DeepSeek models with DeepSeek's official setup script, verify the result, and restore your previous configuration.
- [Inside DeepSeek Harness and Its Plugin-Based Agent Runtime](https://hqman.me/blog/deepseek-harness-agent-runtime.md): DeepSeek Harness separates models, tools, sessions, permissions, and interfaces into plugins that builders can replace and combine.
- [DeepSeek V4 Flash Review: Where It Fits in an Agent Workflow](https://hqman.me/blog/deepseek-v4-flash-review.md): A hands-on look at DeepSeek V4 Flash 0731, its vendor-reported agent benchmarks, and the coding tasks where I would use it.
- [How I Choose GPT-5.6 Sol, Terra, Luna, and Effort Levels](https://hqman.me/blog/gpt56-model-selection.md): A practical decision guide for choosing a GPT-5.6 model and reasoning effort level based on task difficulty, speed, and iteration cost.
- [LoopX: A Local Control Plane for Long-Running Agent Work](https://hqman.me/blog/loopx-control-plane.md): LoopX keeps goals, evidence, ownership, quotas, and handoffs stable across long-running agent sessions without replacing the agent runtime.
- [How to Get More Value from Claude Code Sessions](https://hqman.me/blog/maximize-claude-code-sessions.md): Practical Claude Code habits that reduce context noise, protect prompt cache reuse, and keep recurring work in smaller sessions.
- [Give a Text-Only Coding Agent Vision with ModLens](https://hqman.me/blog/modlens-vision-text-models.md): Use ModLens to route screenshots and image files through a configured vision engine, then return structured evidence to a text-only coding agent.
- [Run Qwen3.8-27B Locally on Apple Silicon](https://hqman.me/blog/qwen38-local-mac.md): Install an Unsloth GGUF build of Qwen3.8-27B with Ollama or llama.cpp, then choose a quant that leaves enough unified memory for the runtime.
- [LLM Inference Handbook: The Missing Serving Guide](https://hqman.me/blog/llm-inference-handbook.md): Same model, different inference stack, wildly different latency and cost. Modular's handbook covers VRAM math, KV cache, batching, and serving.
- [Codex Just Shipped Two Features That Matter](https://hqman.me/blog/codex-voice-multi-folder.md): A practical look at ChatGPT Voice and multi-folder projects in Codex, including their workflow benefits, limits, and setup details.
- [Can Kimi K3 Handle a Real Production Backend?](https://hqman.me/blog/kimi-k3-production-backend-audit.md): A hands-on Kimi K3 backend audit across 68K lines of FastAPI code, including query fixes, measured results, and the full task cost.
- [Product Photos to Interactive 3D on the Web](https://hqman.me/blog/product-photos-interactive-3d.md): How img2threejs turns product photos into editable Three.js code for interactive web demos without a traditional 3D model file.
- [Running Kimi K3 Inside Codex](https://hqman.me/blog/kimi-k3-inside-codex.md): A step-by-step setup for running Kimi K3 inside the Codex app through CC Switch, with routing details and model-picker caveats.
- [From Loop to Graph Engineer: The 5-Layer Stack](https://hqman.me/blog/loop-to-graph-engineer.md): Prompt, context, harness, loop, graph: five stacked layers that move reliability out of the model and into the system around it.
- [AI Is Turning Everyone Into a DevOps Engineer](https://hqman.me/blog/agent-server-setup.md): A DigitalOcean migration that used to take half a day. I set up SSH, described the target state, and Codex did the rest.
- [How I Use GPT-Live to Learn Faster](https://hqman.me/blog/gpt-live-learning.md): GPT-Live can listen and talk at the same time. Drop a Skill or article into ChatGPT and interrupt until the workflow actually clicks.
- [GPT-5.6 Sol Wiped a Developer's Mac. Protect Yours.](https://hqman.me/blog/gpt56-sol-file-deletion.md): On July 10, GPT-5.6 Sol deleted a tester's home directory after a failed $HOME expansion. How the incident happened, and three layers of defense.
- [Grok 4.5: Opus-Level Model, Faster and Cheaper, Now in Cursor](https://hqman.me/blog/grok-45-opus-level-release.md): SpaceXAI released Grok 4.5 for coding and agents. It is in Cursor on all paid plans, with launch discounts through July 14.
- [Tencent Hy3: Free on OpenRouter Until July 21](https://hqman.me/blog/hy3-openrouter-free.md): Tencent open-sourced Hy3, a 295B MoE with 21B active parameters. OpenRouter is running it for free until July 21.
- [pxpipe: Cut Your Fable 5 Bill by 70% With One Proxy](https://hqman.me/blog/pxpipe-token-hack.md): A local Claude Code proxy that renders bulky text as images so Fable 5 bills pixel tokens instead of 92k-character tool dumps.
- [MinerU: PDF to Markdown with OCR, Fully Local](https://hqman.me/blog/mineru-ocr-local.md): Convert PDFs to Markdown with LaTeX formulas and extracted images on your own machine. MinerU runs offline with OCR for 109 languages.
- [Fable 5 Is Back, Sonnet 5 Costs More Than You Think](https://hqman.me/blog/fable-5-sonnet-5-builder-update.md): Fable 5 reopens on July 1 and Sonnet 5 is the new default. Usage, pricing, and why the cheaper sticker can still cost more.
- [Headroom: Context Governance for Coding Agents](https://hqman.me/blog/headroom-context-governance.md): Headroom sits between your agent and the model, classifying and compressing tool output before it fills the context window.
- [Turn Articles into Animated System Diagrams: Visual Flow GIF](https://hqman.me/blog/visual-flow-gif.md): A small skill that extracts system structure from an article, writes a JSON spec, and renders an animated GIF with Python and Pillow.
- [Agents can now deploy to Cloudflare without signing up](https://hqman.me/blog/cloudflare-temporary-accounts.md): Wrangler --temporary gives an agent a 60-minute Cloudflare account, a live workers.dev URL, and a claim link. No OAuth, no MFA, no human click.
- [GPT-5.5 Silently Throttles Reasoning for Third-Party Clients](https://hqman.me/blog/gpt55-reasoning-throttle.md): Third-party GPT-5.5 clients can cap reasoning at 516 tokens. You pay full price and may get a weaker answer.
- [Codex Is Burning Through Your SSD. Here's How I Stopped It](https://hqman.me/blog/codex-ssd-disk-wear-fix.md): A practical guide to checking Codex's SQLite log writes, blocking the unwanted inserts, and protecting your SSD without deleting conversation history.
- [GLM 5.2 vs Opus 4.8: Frontend Dashboard Test](https://hqman.me/blog/glm-52-vs-opus-48-frontend-test.md): A head-to-head frontend test of GLM 5.2 against Opus 4.8, plus Design Arena rankings, pricing, and the caveats that still matter.
- [Codex Can Now Copy Your Actions](https://hqman.me/blog/codex-record-replay.md): Codex Record and Replay watches a Mac workflow once, turns it into an editable Skill, then reruns it with new inputs. macOS only, not in the EU.
- [Doubao's Agent Architecture: 25 Skills, 283 Files](https://hqman.me/blog/doubao-agent-skills.md): A leaked Doubao skill pack shows 25 modular skills and 283 files organized around real work objects, not one giant agent.
- [40 agent loops you can copy into Claude Code or Cursor](https://hqman.me/blog/agent-loop-templates.md): loops.elorm.xyz packages 40 agent loop templates by category so you can copy a kickoff prompt into Claude Code, Cursor, Codex, or Gemini CLI.
- [Fable 5 Is Gone. The System Prompt Isn't.](https://hqman.me/blog/fable-5-system-prompt.md): Claude Fable 5 lasted about 72 hours. The leaked system prompt is still public, and you can load it onto another model.
- [How to make AI-assisted writing sound less like slop](https://hqman.me/blog/humanizer-skill.md): Humanizer is an open-source agent skill that catches 33 AI writing patterns. Pair it with your own voice samples and ship cleaner drafts.
- [Fable 5 One-Shotted This 3D Globe Visualization](https://hqman.me/blog/fable-5-one-shot-globe.md): One screenshot and one prompt. Fable 5 rebuilt a production-looking Three.js globe dashboard in a single pass.
- [Claude Fable 5: Save the Best Model for Hard Stuff](https://hqman.me/blog/claude-fable-5.md): Claude Fable 5 leads on hard coding benchmarks, but the cost is high. Send the hard work to it and keep everyday tasks on cheaper models.
- [Loop Engineering: 14-Step Agent Builder Roadmap](https://hqman.me/blog/loop-engineering-14-step-roadmap.md): A practical roadmap for deciding whether to build an agent loop, then adding automation, state, verification, tools, and security controls in the right order.
- [Loop Engineering: The Next Layer After Prompt Engineering](https://hqman.me/blog/loop-engineering-next-layer.md): Peter Steinberger and Boris Cherny both say the job is designing loops, not writing prompts. Feedback, stop conditions, and token cost decide if it works.
- [A Practical Guide to Using /goal in Codex](https://hqman.me/blog/codex-goal-completion-contract.md): Use Codex goals as completion contracts with explicit outcomes, verification, constraints, iteration rules, and safe stop conditions.
- [Codex Is No Longer Just a Coding Tool](https://hqman.me/blog/codex-industry-plugins.md): OpenAI repositioned Codex for knowledge work with role-specific plugins, hosted Sites, and Annotations. Non-developers are growing fastest.
- [MiniMax M3: Opus-Level Coding, DeepSeek Pricing](https://hqman.me/blog/minimax-m3.md): MiniMax M3 launched with 1M context, near-Opus coding scores, DeepSeek-like API pricing, and two ways to try it immediately.
- [Used Codex to figure out what was eating my Mac's storage](https://hqman.me/blog/codex-storage-cleanup.md): A read-only Codex prompt that turned macOS System Data into a prioritized storage map, with 180 GB reclaimable on a 1TB Mac.
- [Let Codex Distill Your Own Workflow](https://hqman.me/blog/codex-self-audit-workflow-community.md): How Codex can review your recent work, find repeated manual workflows, and turn the best ones into reusable skills, agents, or automations.
- [Recreate the Viral 3D Medical Teaching Model in 4 Steps](https://hqman.me/blog/3d-medical-teaching-model-4-steps.md): Rebuild a classroom-ready 3D anatomy viewer with AI-generated images, 3D reconstruction, GLB compression, and a coding agent.
- [How to Build a Self-Improving Company with AI](https://hqman.me/blog/self-improving-company-ai.md): YC partner Tom Blomfield's framing: make company knowledge machine-readable, then run loops that sense, decide, act, and improve overnight.