Token Efficiency

Make responses and agent work cheaper to read and to run without losing correctness: concise answers, TL;DR, brief status updates and final summaries, just-the-code replies, and lean tool use that avoids rereading files, dumping logs, and repeating checks. Use whenever the user asks to be brief, short, or concise, says "less text", "just the code", "TLDR", or "save tokens", complains about limits or cost, or runs a long session where context is filling up. Puts the answer first, keeps the evidence, failures, and caveats that change decisions, replies in the user's language, and never trades co

9 stars 2 forksSoftware Development

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add prangishviliAbe/agent-skills --skill token-efficiency
Manual install
git clone --depth 1 https://github.com/prangishviliAbe/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/token-efficiency ~/.claude/skills/token-efficiency

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Token and Context Efficiency

Efficiency means more useful information per word read and per token spent. It applies to how results are communicated and how work is carried out. It never applies to how well the work is done: the investigation is as thorough, the code as complete, and the design as finished as the task requires.

## Output

| Rule | Detail |
| --- | --- |
| Answer first | The first sentence is the result, the answer, or the decision needed. Background follows only if it changes what the reader does |
| No ceremony | No praise of the question, restating the request, announcing what is about to be said, or closing offers and summaries of what was just said |
| One statement, once | Do not repeat a point in a list and again in a conclusion |
| Shape fits content | Prose for one idea or a line of reasoning; bullets for parallel independent points; a table only for comparison across the same attributes; code blocks for anything to copy |
| Length fits the question | A yes-or-no question gets yes or no plus the reason. A request for depth gets depth |
| Show the change, not the file | Link or name the location and give the focused diff or the key lines. Full files only when asked or when the file is new and short |
| Keep what decides | Never cut: failures, errors, unverified parts, risks, required user actions, and numbers with units |
Read the full skill on GitHub

Details

Skill name
token-efficiency
Path
token-efficiency/SKILL.md
Repo updated
14 November 2026

FAQ

What does the Token Efficiency skill do?

Make responses and agent work cheaper to read and to run without losing correctness: concise answers, TL;DR, brief status updates and final summaries, just-the-code replies, and lean tool use that avoids rereading files, dumping logs, and repeating checks. Use whenever the user asks to be brief, short, or concise, says "less text", "just the code", "TLDR", or "save tokens", complains about limits or cost, or runs a long session where context is filling up. Puts the answer first, keeps the evidence, failures, and caveats that change decisions, replies in the user's language, and never trades co

How do I install the Token Efficiency skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add prangishviliAbe/agent-skills --skill token-efficiency. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Token Efficiency popular?

It lives in prangishviliAbe/agent-skills, which has 9 GitHub stars and 2 forks.

Related skills

Anti AI Slop Design

9

prangishviliAbe/agent-skills

Design, refine, implement, or critique websites, landing pages, dashboards, apps, and components so nothing looks AI-generated or templated. Use for "looks AI", "too generic", "make it premium", "make it look better", art direction, redesigns, visual polish, a page or component designed from scratch, or a review of how a UI looks, including Georgian and multilingual layouts. Covers every layer where slop appears: page structure, typography, color, spacing, surfaces, icons, imagery, copy, motion, and the code that produces them. Replaces default choices with decisions derived from the subject,

AI, LLMs & Agents

Premium Web Motion

9

prangishviliAbe/agent-skills

Design, implement, tune, and debug web motion: hover and press feedback, menus, dialogs, drawers, accordions, toasts, page and view transitions, list reordering, drag and gesture feedback, scroll-driven effects, loading states, and motion tokens, in CSS, the Web Animations API, React, Motion, GSAP, and component libraries. Use for "add animation", "make it feel smoother or more premium", janky, slow, or glitchy transitions, animations that break when interrupted, reduced-motion support, or a review of how a UI moves. Gives every motion a purpose, exact duration and easing, interruption safety,

Frontend & Design

Security

9

prangishviliAbe/agent-skills

Security engineering for web applications, APIs, and the AI agents and tools around them. Use to audit code or architecture, check whether a suspected flaw is exploitable, threat-model a feature, or harden sign-in, sessions, OAuth, access control and tenant isolation, injection, XSS, CSRF, SSRF, file uploads, cryptography and secrets, webhooks, race conditions, dependencies and CI/CD, WordPress, and prompt injection or tool permissions in LLM agents; also for "is this secure", leaked keys, dependency alerts, and incident triage. Traces real attack paths from attacker input to impact, reports e

Security

Web Development

9

prangishviliAbe/agent-skills

Build, fix, review, refactor, and ship web software in the existing stack: React, Next.js, and TypeScript front ends; Node, Python, and PHP back ends; REST and GraphQL APIs; SQL databases and migrations; payments, webhooks, and third-party integrations; forms and sign-in flows; WordPress and WooCommerce; CI and deploys. Use for implementing a feature, diagnosing a bug or flaky test, speeding up a slow page or query, reviewing a diff, upgrading a framework, or vague asks like "make this work" or "why is this broken". Reads the project first, uses the installed versions' real APIs, enforces trus

Software Development

Clean Code

9

DIL8654/claude-code-dotnet-template

Prefer small, explicit, readable C# code and pragmatic refactoring. Use for cleanup, maintainability reviews, naming improvements, duplication removal, and simplifying overly complex implementations.

Software Development

Seekdb CLI

9

oceanbase/oceanbase-skills

Use seekdb-cli to interact with seekdb/OceanBase databases via shell commands. Use when: (1) querying databases with SQL, (2) exploring table schemas and structure, (3) profiling table data distributions, (4) inferring table relationships, (5) managing vector collections and semantic search, (6) adding/exporting collection data, (7) managing AI models , (8) checking database connection status, or (9) performing any database operation via command line.

Software Development

Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.