Skip to main content
skill CX Codex

token-efficiency · nickcrew — Claude Code skill: compressed agent language

token-efficiency — a Claude Code skill that switches the agent to compact notation — symbols and abbreviations instead of full sentences. Kicks in when the context window is nearly full or a short status line is enough.

MIT 245 installs ★ 71 updated 2026-06-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add NickCrew/Claude-Cortex --skill token-efficiency -a claude-code
Open on GitHub

What token-efficiency does

Installs into Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. The skill defines a symbol dictionary in three groups: logic and flow (→, ⇒, ∴, ∵), statuses (✅, ❌, ⚠️, 🔄, ⏳), and domains (⚡ performance, 🔍 analysis, 🛡️ security, 🏗️ architecture).

Frequent terms get short forms: cfg, impl, deps, val, perf. A sentence like “the authentication system has a security vulnerability in the user validation function” becomes auth.js:45 → 🛡️ sec risk in user val().

Inside there is only a SKILL.md with symbol tables and examples. The agent switches to compressed mode when context is above 75% full, during large codebase analysis, in multi-step workflows, or when the user asks for brevity. Emoji statuses render inconsistently across terminals and fonts — some will show as boxes.

What it helps with

  • shrink agent replies when context is almost full
  • report build, test and deploy status in one line
  • tag a task type with a domain symbol
  • replace frequent terms with short abbreviations
  • keep one compressed vocabulary across a team

Example prompts for the agent

  • Compress replies using the token-efficiency symbol system
  • Give me the build status as build ✅ ” test 🔄 ” deploy ⏳
  • Context is at 80%, switch to token-efficiency notation

How to install token-efficiency

1Skills CLI (Vercel)

npx skills add NickCrew/Claude-Cortex --skill token-efficiency -a claude-code

2Manually: put the files in place

~/.claude/skills/token-efficiency/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/token-efficiency/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about token-efficiency

How do I install token-efficiency in Claude Code?

Run npx skills add NickCrew/Claude-Cortex --skill token-efficiency -a claude-code. The skill file lands in ~/.claude/skills/token-efficiency/SKILL.md.

What does token-efficiency do?

It introduces a compressed notation: symbols for logic and status, plus abbreviations like cfg and impl. The agent falls back to it when context is tight or short answers are needed.

When does the compressed mode actually activate?

Per the skill conditions: context above 75% full, large codebase analysis, complex multi-step work, or an explicit request from the user for brevity.

Source text

SKILL.md · MIT
---
name: token-efficiency
description: Compressed communication using symbols and abbreviations. Use when context is limited or brevity is needed.
keywords:
  - compressed communication
  - abbreviations
  - token
  - efficiency
  - token efficiency
---

# Token Efficiency

Compressed communication for limited context windows.

## Symbol System

### Logic & Flow
| Symbol | Meaning |
|--------|---------|
| → | leads to, implies |
| ⇒ | transforms to |
| ← | rollback |
| & | and |
| \| | or |
| » | sequence/then |
| ∴ | therefore |
| ∵ | because |

### Status
| Symbol | Meaning |
|--------|---------|
| ✅ | complete/pass |
| ❌ | failed/error |
| ⚠️ | warning |
| 🔄 | in progress |
| ⏳ | pending |

### Domains
| Symbol | Domain |
|--------|--------|
| ⚡ | performance |
| 🔍 | analysis |
| 🛡️ | security |
| 🏗️ | architecture |

## Abbreviations
- `cfg` config
- `impl` implementation
- `deps` dependencies
- `val` validation
- `perf` performance
- `sec` security
- `err` error

## Examples

**Standard:**
> "The authentication system has a security vulnerability in the user validation function"

**Compressed:**
> `auth.js:45 → 🛡️ sec risk in user val()`

**Standard:**
> "Build completed, now running tests, then deploying"

**Compressed:**
> `build ✅ » test 🔄 » deploy ⏳`

## When to Use
- Context >75% full
- Large codebase analysis
- Complex multi-step workflows
- User requests brevity

© NickCrew · MIT · NickCrew/Claude-Cortex

Similar skills

All skills for Agent setup: memory, context, orchestration →

token-efficiency by other authors comes first.

token-efficiency Delphine-L token-efficiency — a Claude Code skill that cuts unnecessary file reads and command output. It guides token-conscious codebase exploration and development. CX Codex +1 2,700installs token-efficiency SuperClaude-Org token-efficiency switches the agent into a compressed output mode: bullets, tables, abbreviations. Useful when context runs low or the task is large. CX Codex +1 ★ 23,950repo stars token-efficiency Rohit Ghumare token-efficiency cuts conversational fluff, caps tool executions per task, and stops Claude Code from repeatedly editing working implementations. CX Codex +1 ★ 2,966repo stars caveman JuliusBrussee caveman — a skill for Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode that switches responses to ultra-compressed mode without articles or filler words. Cuts token usage by around 75%, technical accuracy intact. CX Codex +1 3,800installs Wallet Portfolio — Multi-Chain Token Holdings axel-belfort The Wallet Portfolio — Multi-Chain Token Holdings MCP server for Claude Code tracks ETH and ERC-20 tokens, showing USD values and 24-hour changes. CX Codex +1 5,148installs gmgn-token GMGNAI gmgn-token is a Claude Code skill that checks a token by address, returning price, liquidity, holder data, and security details. It runs on requests about a token or a pre-purchase check. CX Codex +1 20,400installs Token Enhancer xelektron Token Enhancer is an MCP server that trims web pages to plain text before your agent reads them. A Yahoo Finance fetch drops from 704,760 tokens to 2,625. CX Codex +1 ★ 68repo stars token-optimizer ooples token-optimizer cuts token usage 60-90% in Claude Code and Codex using caching, compression, and selective file reading. CX Codex ★ 1,596repo stars runai-get-utilization-overview Run:ai runai-get-utilization-overview is a Claude Code skill that checks whether projects and departments on a Run:ai cluster are using allocated GPUs or leaving them idle, and ranks them by utilization. CX Codex +1 ★ 4,106repo stars

From the same set21

The whole set →
react-performance-optimization react-performance-optimization guides React rendering optimization, memoization, code splitting, and list virtualization. Useful when diagnosing slow components or trimming initial bundle size. CX Codex +1 1,900installs owasp-top-10 Security audit guide based on OWASP Top 10 2021. Helps agents spot injection flaws, broken access controls, and authentication issues during code reviews. CX Codex +1 760installs ui-design-aesthetics The ui-design-aesthetics skill feeds the agent rules for typography, color and motion so generated interfaces stop looking like default AI output. Useful when starting a feature or reworking an existing screen. CX Codex +1 362installs threat-modeling-techniques threat-modeling-techniques — a skill for threat modeling: walks the system through STRIDE, builds attack trees and scores risk with DREAD. Best used before the code exists. CX Codex +1 357installs repo-cleanup repo-cleanup — a skill for structured repository cleanup: removes dead code, unused dependencies, outdated docs, and flaky tests with usage checks, archiving, and validation steps built in. CX Codex +1 183installs helm-chart-patterns helm-chart-patterns is a Claude Code skill for developing Kubernetes Helm charts, covering template structure, values.schema.json validation, lifecycle hooks, and multi-environment setups. CX Codex +1 179installs typescript-advanced-patterns The typescript-advanced-patterns skill helps apply advanced TypeScript types to APIs and domain models. Use it when compile-time rules need to express states, constraints, or distinct identifiers. CX Codex +1 174installs code-explanation The code-explanation skill explains code, architecture, and system behavior at a depth that matches the reader. Use it for walkthroughs, teaching, and knowledge transfer. CX Codex +1 173installs

Project sponsors

Companies that keep this analytics open