Toggle TL;DR response mode. When on, Claude answers maximally concisely unless you explicitly ask for a full explanation.
A toggle for people tired of bible-sized AI responses.
One slash command · ~93 tokens per message when on, zero when off · No per-project setup · Persists across sessions
You asked Claude what time it is. Three paragraphs later, you have a brief history of horology, an explainer on UTC offsets, and a caveat about leap seconds. You wanted "3:47pm".
tldr is a tiny Claude Code plugin that adds one slash command: /tldr:tldr. Flip it on and Claude defaults to 1-3 sentence replies for every subsequent message. Ask for "detail" or "explain" and you get the full essay anyway — your call, every turn.
/plugin marketplace add https://github.com/marcelopaniza/tldr
/plugin install tldr@tldr
/tldr:tldr # toggle (default)
/tldr:tldr on
/tldr:tldr off
/tldr:tldr status
State lives at ~/.claude/plugins/data/tldr/state and persists across sessions and projects. Toggle once, applies everywhere until you flip it off.
/compact waits longerx if cond else y"| State | Per user message | Why |
|---|---|---|
| Off | 0 tokens | Hook exits silently before Claude sees anything |
| On | ~93 tokens | Hook prepends a short instruction telling Claude to be terse, with an exception clause for when you ask for detail |
No persistent context, no system-prompt rewriting, no daemon — just a UserPromptSubmit hook that reads a one-byte state file.
If your message contains any of these phrases, tldr yields and Claude gives you the full answer for that turn:
So tldr is on most of the time, and you opt back into the bible when you actually need it.
bash (any reasonably modern version)Test without installing:
claude --plugin-dir /path/to/this/repo
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub marcelopaniza/tldr --plugin tldrYour Claude memory companion. Turn it on, keep it lean, schedule the upkeep, reverse anything.
Compress Claude instruction files (CLAUDE.md, memory files, SKILL.md) into denser YAML. Verified lossless by meaning via round-trip review. Runs inside Claude Code; no API key required.
Lightweight cross-terminal messaging for Claude Code. Multiple sessions on one or many machines share a folder; messages arrive on the next prompt, at session start, and — on by default — the instant they land, waking an idle session in real time. Zero token cost when no traffic.
Lightweight cross-terminal messaging for Claude Code. Multiple sessions on one or many machines share a folder; messages are picked up by a hook on the next user prompt — zero idle polling, zero token cost when no traffic.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.