Remembrandt — Development skill for Claude Code
skill you drop into any agent (Claude Code, Cursor, Codex) plus a zero-dependency CLI.
How to install Remembrandt
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open rishibanota/remembrandt and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Remembrandt does
skill you drop into any agent (Claude Code, Cursor, Codex) plus a zero-dependency CLI.
Alternatives in Development
- Understand Anything — Graphs that teach graphs that impress 80.7k ★
- Ccusage — CLI for analyzing Claude Code/Codex usage from local JSONL files 11.8k ★
- Haft — Engineering decisions engine that know when they're stale 1.4k ★
README
remembrandt
Never forgets. Persistent memory for Claude Code, Cursor and Codex coding agents.
Your coding agent forgets everything between sessions. remembrandt is a tiny skill + CLI that gives it a durable, human-readable memory — so it picks up exactly where it left off: the decisions, the gotchas, the changelog. Always.

🤔 The problem
You spend 20 minutes re-explaining your architecture to Claude Code, Cursor or Codex. It answers, you close the terminal… and the next session it asks the *same questions* again. Context is rebuilt from scratch every single time.
**That is the #1 complaint about coding agents.** They're brilliant — and completely amnesiac.
✨ The fix
remembrandt is a **skill you drop into any agent** (Claude Code, Cursor, Codex) plus a **zero-dependency CLI**. It maintains a lightweight, file-based memory store for your project and regenerates a `MEMORY.md` your agent reads at the start of every session.
Your agent finally remembers: the rationale behind that `why`, the footgun it hit yesterday, what shipped last week — without you repeating a word.
📸 Demo
$ remembrandt remember "Use uv for dependency management" --category decision --tags uv
Remembered entry #1 in 'decision'.
$ remembrandt remember "Never mutate the shared config object" --category gotcha
Remembered entr
Related Skills
Sync Skills
Zero-dependency Bash CLI that syncs agent skills across Claude Code, Cursor, Codex and Gemini CLI.
Coding Agent Rules
Ten Commandments for Coding Agents — a minimal AGENTS.md / CLAUDE.md drop-in for Claude Code, Codex, Gemini CL
Albert
Autonomous multi-agent harness for Claude Code (A.L.B.E.R.T. orchestrator) plus a zero-dependency live HUD con
Claude Cursor Proxy
Local proxy so Claude Code and grok-build (Grok CLI) can use Cursor models (Fable), plus Codex, Kimi, and Grok
Agentcompat
Which agent extension features actually work on which agent. A compatibility matrix for skills, hooks, MCP and
Skill Indexer
Zero-config CLI that scans your npm dependencies for SKILL.md directories, validates them, and installs them i
Related Agents
Monk Installer
Install, upgrade, and troubleshoot monk-agent plus Monk CLI/daemon for Claude, Codex, and Cursor users.
Async Code
Use Claude Code or CodeX CLI to perform multiple tasks in parallel with a Codex-style UI, functioning as a per
Independent Reviewer
Product-technical alignment reviewer. Spawned in a tmux pane via OpenAI Codex CLI with zero inherited context.