Writing log71 posts291 tagslatest Nov 4, 2026
Claude-code.
Latest posts
Lemo-Opuscar: How Do You Package 66 Film Styles as Code and Prompts?
Lemo-Opuscar is a style library that lets a coding agent draw, score and mix a short film in styles like watercolour, ukiyo-e or a satellite briefing. The renderer is under 400 lines; the real body is about 300,000 words of style prompts and directing guides. I followed the code, rendered demos myself, and measured how speed scales with workers and whether the output is really identical.
Hallmark Architecture: How Do You Stop Designs From Looking 'AI-Generated' — With a Prompt?
Hallmark is Together AI’s anti-AI-slop design skill. It ships almost no executable code — its entire intelligence lives in 106 markdown files. This piece dissects the SKILL.md router and its progressive context loading, the narrowing decision pipeline, and — at its center — the 58 slop-test gates, contrasting it with skill-injecting projects like Superpowers and SkillSpector.
Analyzing ponytail: How Does a Skill That Makes Agents "Write Less Code" Ship to 16 Agents?
ponytail packs a single discipline — the "lazy senior dev" laziness ladder — into one SKILL.md and ships it to 16 agents via every mechanism (skill, hook, command, MCP, plugin), proving a ~54% code cut with a real agentic benchmark. We analyze it against Superpowers, and the idea that a skill is a bundle of discipline, distribution, and measurement rather than code.
spec-kit vs superpowers: Two Ways to Give a Coding Agent a "Process"
GitHub's spec-kit and Anthropic's superpowers plugin both force a workflow onto coding agents so they never drift into vibe coding. But one is a spec-first file system that leaves the specification behind as an artifact in a .specify/ directory, while the other is a collection of discipline prompts lazily loaded through the Skill tool. We compare the two projects across distribution model, artifact philosophy, token cost, and extensibility.
Ruflo Architecture: Building an Agent Operating System on Top of Claude Code
Ruflo extends Claude Code with a CLI, MCP server, swarm coordination, AgentDB memory, hooks, background workers, a plugin marketplace, and a Web UI to create a multi-agent operations layer. This post analyzes the architecture of Ruflo — an evolution from Claude Flow — and connects it to earlier posts on agentmemory, Superpowers, and Hermes Agent.
Claude Code Game Studios Architecture Analysis: Running Claude Code Like a Game Development Studio
An analysis of how Claude Code Game Studios combines 49 agents, 72 skills, hooks, rules, and templates to run a single Claude Code session like a game development studio.
Using Superpowers: Changing How I Work with Agents
An analysis of Superpowers — a skill library that injects disciplined development practices like TDD, debugging, brainstorming, and code review into AI coding agents — covering its architecture and design philosophy.