skills.rest
sburl
sburlCOMMUNITY
Explore all skills by this author →
Website𝕏@sqburlGitHub

napkin

Initialize and update repo-scoped memory in .codex/napkin.md.

26|2|Updated Feb 12, 2026
Search Tags:#curation#codebase#memory#session#repo#napkin
One-click install
npx skills add https://github.com/sburl/CrossCheck --skill napkin-sburl
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: napkin
Source: https://github.com/sburl/CrossCheck/tree/main/codex/skills/napkin
Command: npx skills add https://github.com/sburl/CrossCheck --skill napkin-sburl

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Per-repo behavioral memory stored in .codex/napkin.md. Use to initialize or update the napkin for any project. Tracks repo-specific mistakes, user corrections, and surprising gotchas that recur across sessions. Read silently at session start if the file exists. Write during work. Curate aggressively. Complement to MEMORY.md (which is cross-project and user-scoped); napkin is repo-scoped and committable.

Core Features & Use Cases

  • Initialize or update a napkin for a project to capture recurring patterns and gotchas.
  • Read napkin silently at session start to bias behavior and reduce mistakes.
  • Curate and prune entries to keep the repository memory relevant and compact.

Quick Start

Initialize napkin for this repository at the start of a session to have it guide your behavior.

Frequently Asked Questions about napkin

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I store repo-specific memory to prevent recurring coding mistakes across sessions?▼

Store repo-specific memory in a committable `.codex/napkin.md` file to track mistakes, corrections, and gotchas. The file is read silently at session start to bias behavior and reduce recurring errors during coding and reviews.

What is the best way to maintain codebase memory relevance and compactness over time?▼

Maintain codebase memory relevance by aggressively curating and pruning entries within the napkin file. Use the curation workflow during work sessions to update memory and remove outdated repository learnings, keeping the file compact.

Does per-repo behavioral memory work alongside cross-project user-scoped memory files?▼

Per-repo behavioral memory complements cross-project user-scoped memory files. While user memory applies across all projects, repo-scoped memory travels specifically with the codebase and can be committed directly to version control.

How do I initialize memory for a project to guide behavior during code reviews and troubleshooting?▼

Initialize memory for a project by creating the napkin file at the start of a session. This captures recurring patterns and surprising gotchas, which are then read silently to guide behavior during coding, reviews, and troubleshooting.

When should I not use repository-scoped memory for tracking session learnings?▼

Avoid using repository-scoped memory for cross-project user preferences or global settings. It is specifically designed for repo-specific mistakes and corrections that should travel with and be committed to an individual codebase.

Related Skills

Explore More Software Engineering Skills→
paulmalmquistpaulmalmquist

winston-session-bootstrap

Initialize Winston repo-local sessions by loading startup context files and confirming repo root.

Community
Basic
eszxcvfdeszxcvfd

note

Save and manage persistent notes in .omx/notepad.md across sessions.

Community
Intermediate
ano4lano4l

promote

Promote proven patterns from MEMORY.md into enforceable CLAUDE.md or .claude/rules.

Community
Advanced
mpazarynampazaryna
1

prime-web-dev

List Git-tracked files, read README.md and CONTEXT.md, and summarize web project structure.

Community
Basic