A Claude Code config rule marked MANDATORY was skipped twice in one session. Here's the root cause — three architectural reasons why emphasis doesn't work — and three system-level solutions that do.

How I replaced screenshot-heavy iOS test runs with ui_describe_all-first testing in Claude Code, cutting context usage by 81% for BPS Tracker. Plus Fastlane integration for App Store automation.

A custom /debate command that pits Codex CLI against Gemini CLI on architecture, code, and decisions. Different training data, different blind spots — and the disagreements between them are usually the most useful output.

Building a multi-agent orchestrator with `claude -p` subprocess reveals a silent data loss problem. The SDK fix, session resume, parallel execution, and why setting_sources matters.

Your CLAUDE.md and MEMORY.md grow silently until they eat 10K+ tokens per turn. I built a /slim skill that lets Claude diagnose and fix its own bloat — here's how.

You just started using Claude Code and the context window keeps filling up. Here's where the tokens actually go, what you can do about it, and how to make Claude remember things without re-reading everything.

I ran sysprog21/zhtw-mcp across 72 of my Traditional Chinese articles. Three sweeps, 128 cross-strait substitutions across 42 files. The real takeaway wasn't the count — it was discovering my blindspot isn't 'I don't know the right Taiwanese term,' it's 'when a Mainland term shows up I don't auto-doubt it.'

I had a rule called 'fact-check before publishing.' I still shipped three fabrications. The problem wasn't the rule — it was where I put it. This is how I promoted it from skill to hook: a small script guarding the moment I press 'send,' so I can't even try without verification.

When an AI coding CLI runs out of quota mid-task, what dies isn't your knowledge base — it's the live state trapped in the session. A file-based handoff protocol lets Claude Code and Codex resume each other's half-finished work.

How I hand engineering tasks to Codex: self-contained ticket files with machine-checkable acceptance, background execution, three flags I paid for in dead time, and a report-is-not-a-result gate.

I set out to retire a 'dead' shared-memory folder my knowledge base had replaced. It was writing to itself at 2:30 AM. Three traps in doctrine-vs-runtime drift, and why you map a memory system's topology from the hub, not the spoke.

My AI's long-term memory is ~600 markdown files in three layers: the files are the source of truth, a search engine makes them findable, and a knowledge graph links them by concept. Here's the design, why each layer exists, and the wrong turns I took building it.

Search finds an AI agent's notes but hands back raw material to re-derive each session. I distill ~600 files into canonical claims — the goal is ending re-explanation, not enforcing agreement.

Six posts in, my AI setup is really two axes of one system: durable knowledge and live task state, both in plain files. Here's how they converge so different AIs hand off work without re-explaining it or losing it.

One of my AI agents was auto-loading 193 skills into a 2% context budget, silently truncating every description. The fix was visibility governance, not deletion — an allowlist, thin-shell skills, and three layers that stop it re-bloating.

My AI agent's durable memory auto-saved a wrong answer, then cited it back as fact — outranking the corrected truth. The three-part pathology, and why the fix is ranking memory, not adding more of it.

A draft cleared fact-check and two rounds of native-speaker review, then one reader caught it in a sentence. The check that should have caught it was labelled manual, so it had never run. Here's the script that replaced it, and how I calibrated the thresholds.

Dissecting 41 Codex sessions turned up a wall-clock formula (tool calls x 14.3s) and cut a stuck ticket from 41 minutes down to 73 seconds.

A COLM 2026 paper strips every style signal from 61,608 stories and still tells human from AI at 93.2% macro-F1. The tell is structure, not em-dashes.

Preset TTS voices don't sound like you. Zero-shot cloning with Qwen3-TTS and mlx-audio needs 24 seconds of reference audio and ten lines of Python, all local.

Claude Code mods let a plugin draw a live pane in your session. Six prompts, each run in a fresh session, build a GPU, disk, quota and local-model dashboard.

I tested EmbeddingGemma 2 against v1 on my AI's note search on an M1 Max: recall@5 went from 50% to 58.3%, code search improved, and memory rose to 2.75 GiB.