tldr

tldr is a skill for Claude Code, Codex from rodrigooler/claude-code-tldr. It costs 84 tokens per session (578 once invoked), scanned A, original, MIT.

A persistent setting that makes replies very short after the user turns it on. It stays active across messages until the user turns it off.

In plain words
What is it for?
Use it when asking for brief answers, short commands, or a compact result with the next step.
Why use it?
It reduces the effort of reading long explanations or terminal output when only the essential result is needed.

Skill for Claude CodeCodex

Part of the tldr plugin — 1 skill shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/rodrigooler/claude-code-tldr/tldr
Any agent
npx skills add rodrigooler/claude-code-tldr --skill tldr
Clone the repo
git clone --depth 1 https://github.com/rodrigooler/claude-code-tldr

Made for: Claude Code, Codex.

Or install tldr, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tldr

README.md
[![agentmods](https://agentmods.dev/badge/skills/rodrigooler/claude-code-tldr/tldr.svg)](https://agentmods.dev/skills/rodrigooler/claude-code-tldr/tldr)
Your own site
<a href="https://agentmods.dev/skills/rodrigooler/claude-code-tldr/tldr"><img src="https://agentmods.dev/badge/skills/rodrigooler/claude-code-tldr/tldr.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 578 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00084 $0.00578
Opus 5 $0.00042 $0.00289
Sonnet 5 $0.00017 $0.00116
Haiku 4.5 $0.00008 $0.00058

Measured 5d ago against content hash 9725d08d6cd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tldr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/tldr/SKILL.md · 36 lines

What it actually says

tldr — persistent ultra-short mode

What it is

A persistent ON/OFF communication mode. While ON, every reply is ultra-short (≤5 lines) until the user turns it off. Single goal: the user reads the least possible without losing what matters.

Turn on / off

  • On: the user sends /tldr (or "short mode", "be brief", "keep it short", "less text", "tl;dr"). → Confirm in 1 line: 🔅 tldr ON — replies ≤5 lines until you say "tldr off". then apply the rules below to every following reply.
  • Off: the user sends /tldr off (or "turn off tldr", "back to normal", "normal mode"). → Confirm in 1 line and return to the default style.
  • The mode persists across turns. As the conversation grows, do NOT forget it is ON.

Rules while ON (apply to every reply)

  1. Max 3–5 lines. Didn't fit? It's too long — cut more.
  2. Only the actionable essential: the result + the next step. No context, no recap, no preamble.
  3. No filler: no "great question", no "let me explain", no summary of what you are about to do — just do it.
  4. Short bullets, not paragraphs. One idea per line.
  5. Code/commands: show only the snippet that changes, not the whole file.
  6. Plain, direct language.
  7. Does an honest answer need more (critical decision, risk, long step-by-step)? Give the verdict in ≤5 lines and offer: want the detail? say "expand".

When NOT to shorten (shorten the explanation around it, never the artifact)

  • Code the user will paste or run — it must be complete and correct.
  • Security / data-loss warnings — clarity beats brevity.

Red flags — you broke the mode

  • Went past 5 lines → cut.
  • Started with preamble/recap → delete the first sentence.
  • Explained the "why" unprompted → remove it.
  • "But this case is special and deserves context" → no. Give the verdict; offer "expand".
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 36 lines · 84 tokens per session scan A 9725d08d6cd2

Subscribe to this mod's changes

tldr is a skill published in the GitHub repository rodrigooler/claude-code-tldr (3 stars, last pushed 3mo ago), licensed MIT. It adds 84 tokens to every session and 578 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

todos

This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…

JetBrains/thinkrail · 127 tokens

handoff

Checkpoint work for recovery — fires on "handoff", "wrap up", context pressure, a closed phase, or before a long external wait or irreversible gate. Part of the Agentsmith harness; writes durable state plus a paste-ready kickoff block so a fresh session loses nothing.

PromptPartner/agentsmith · 58 tokens

cli-framework-cli-commander

Node.js CLI development with Commander.js and @clack/prompts - command structure, interactive prompts, wizard state machines, config hierarchies, exit codes, cancellation handling.

agents-inc/skills · 41 tokens

cli-prompts-clack

Beautiful interactive CLI prompts with @clack/prompts and custom prompts with @clack/core.

agents-inc/skills · 24 tokens

cli-framework-oclif-ink

Modern CLI development combining oclif's command framework with Ink's React-based terminal rendering.

agents-inc/skills · 25 tokens

tokenless-install

Install, upgrade, repair, and verify Tokenless, its agent skills, and local Playwright runtime. Use only when the user explicitly asks for installation, upgrade, repair, browser sign-in handoff, a failed doctor check, or an installation integrity check.

jazelly/tokenless · 56 tokens