#373 · Primary category: AI Coding Assistants
paperthin
Low-level agentic design patterns. Turning old engineering wisdom into reflexes your agent reaches for on its own—on any agent.
Project last updated:08/18/26
GitHub Stars
911
Forks
95
Contributors
5
License
MIT
Why we included this project
Paperthin doesn't sit on top of your coding agent as another assistant. It installs a pack of small skills into the agent you already run, whether that's Claude Code, Codex, Cursor, or something else, and the model calls them on its own when the task calls for it. Each skill is a focused markdown rule that encodes a classic engineering habit: clean single-purpose code, honest quality gates, documentation that stays current. That way your model applies the same standard without a human restating the instruction on every task. The two-by-two map included in the repo is a helpful frame for deciding when one clean artifact matters more than consistency across many files, which translates directly into how you shape your own review workflow. Small teams tired of their coding agent cutting corners will find this a lightweight way to keep discipline in the loop.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.