{"id":45679640,"url":"https://github.com/blader/napkin","last_synced_at":"2026-03-09T20:01:20.128Z","repository":{"id":336973512,"uuid":"1151885257","full_name":"blader/napkin","owner":"blader","description":"A Claude Code skill that gives the agent persistent memory of its mistakes via a per-repo markdown scratchpad.","archived":false,"fork":false,"pushed_at":"2026-02-07T03:28:18.000Z","size":4,"stargazers_count":82,"open_issues_count":0,"forks_count":3,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-02-07T13:53:54.153Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/blader.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-07T03:08:58.000Z","updated_at":"2026-02-07T13:39:22.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/blader/napkin","commit_stats":null,"previous_names":["blader/napkin"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/blader/napkin","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blader%2Fnapkin","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blader%2Fnapkin/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blader%2Fnapkin/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blader%2Fnapkin/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/blader","download_url":"https://codeload.github.com/blader/napkin/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/blader%2Fnapkin/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30309998,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-09T17:35:44.120Z","status":"ssl_error","status_checked_at":"2026-03-09T17:35:43.707Z","response_time":61,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-02-24T14:00:36.898Z","updated_at":"2026-03-09T20:01:20.115Z","avatar_url":"https://github.com/blader.png","language":null,"readme":"# Napkin\n\nA skill for Claude Code that gives the agent persistent memory of its mistakes.\n\nThe agent maintains a markdown file in your repo (`.claude/napkin.md`) where it tracks what went wrong, what you corrected, and what worked. It reads the file at session start and writes to it continuously as it works. By session 3-5 the behavior shift is significant — the agent stops making mistakes you've already corrected and starts pre-empting issues before you catch them.\n\nBaby continual learning in a markdown file.\n\n## Install\n\n**Claude Code**\n\n```bash\ngit clone https://github.com/blader/napkin.git ~/.claude/skills/napkin\n```\n\n**Codex**\n\n```bash\ngit clone https://github.com/blader/napkin.git ~/.codex/skills/napkin\n```\n\nThat's it. The skill activates every session, unconditionally.\n\n## How it works\n\n1. **Session start**: Agent reads `.claude/napkin.md` in the current repo. If it doesn't exist, it creates one.\n2. **During work**: Agent logs mistakes (its own and yours), corrections, patterns, preferences — as they happen, not just at session end.\n3. **Over sessions**: The napkin compounds. Session 1 is normal. Session 3 the agent is catching things before you do. Session 5 it's a different tool.\n\n## What gets logged\n\n- Agent's own mistakes — wrong assumptions, bad approaches, failed commands\n- Your corrections — anything you told it to do differently\n- Tool/environment surprises — things about the repo that weren't obvious\n- Your preferences — how you like things done\n- What worked — successful approaches worth repeating\n\n## The napkin\n\nLives at `.claude/napkin.md` in each repo. One per repo. The agent designs the initial structure and adapts it to the project's domain.\n\nYou can `.gitignore` it or commit it — your call. Committing it means other contributors' agents benefit from the same learned patterns. Ignoring it keeps it personal.\n\n## License\n\nMIT\n","funding_links":[],"categories":["🧠 Agent Skills","Others"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fblader%2Fnapkin","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fblader%2Fnapkin","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fblader%2Fnapkin/lists"}