/token-efficient
Compress responses to reduce context usage by 30-50%. Trigger with "token efficient mode", "compress responses", "save context", "save tokens".
$ npx -y skills add wasabeef/claude-code-cookbook --skill token-efficient --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/token-efficient
Context preview
The summary Claude sees to decide when to auto-load this skill.
Compress responses to reduce context usage by 30-50%. Trigger with "token efficient mode", "compress responses", "save context", "save tokens".
SKILL.md
token-efficient.SKILL.mddescription: 'Compress responses to reduce context usage by 30-50%. Trigger with "token efficient mode", "compress responses", "save context", "save tokens".'
Compress responses to reduce context usage by 30-50%
Reduces AI response context usage by 30-50% through compression efficiency mode.
Compress responses to reduce context usage by 30-50%
Token Efficiency Mode leverages visual symbols and abbreviation systems to compress Claude's responses. **Generated code quality and content remain unchanged**. Only the explanation method changes.
Usage
# Enable mode
"Respond in Token Efficiency Mode"
"--uc mode"
"Concise mode"
How It Works
1. Symbol System
Logic & Flow
| Symbol | Meaning | Example | | ------ | ---------------- | ------------------------------- | | → | leads to, causes | `auth.js:45 → 🛡️ security risk` | | ⇒ | converts to | `input ⇒ validated_output` | | ← | rollback, revert | `migration ← rollback` | | ⇄ | bidirectional | `sync ⇄ remote` | | & | and, combine | `🛡️ security & ⚡ performance` | | \| | or, separator | `react\|vue\|angular` | | : | define, specify | `scope: file\|module` | | » | then, sequence | `build » test » deploy` | | ∴ | therefore | `tests ❌ ∴ code broken` | | ∵ | because | `slow ∵ O(n²) algorithm` |
Status & Progress
| Symbol | Meaning | Usage | | ------ | ----------------- | ----------------------- | | ✅ | complete, success | Task completed normally | | ❌ | failed, error | Immediate action needed | | ⚠️ | warning | Review recommended | | 🔄 | in progress | Currently active | | ⏳ | pending | Scheduled for later | | 🚨 | urgent, critical | High priority |
Technical Domains
| Symbol | Domain | Usage | | ------ | ------------- | --------------------- | | ⚡ | Performance | Speed, optimization | | 🔍 | Analysis | Search, investigation | | 🔧 | Configuration | Setup, tools | | 🛡️ | Security | Protection, safety | | 📦 | Deployment | Package, bundle | | 🎨 | Design | UI, frontend | | 🏗️ | Architecture | System structure | | 🗄️ | Database | Data persistence | | ⚙️ | Backend | Server processing | | 🧪 | Testing | Quality assurance |
2. Abbreviation System
System & Architecture
- `cfg` → configuration
- `impl` → implementation
- `arch` → architecture
- `perf` → performance
- `ops` → operations
- `env` → environment
Development Process
- `req` → requirements
- `deps` → dependencies
- `val` → validation
- `auth` → authentication
- `docs` → documentation
- `std` → standards
Quality & Analysis
- `qual` → quality
- `sec` → security
- `err` → error
- `rec` → recovery
- `sev` → severity
- `opt` → optimization
Example Comparisons
Example 1: Error Report
**Normal Mode (85 chars)**
Security vulnerability found in the user validation function at line 45 of the auth system.
**Token Efficient (39 chars)**
auth.js:45 → 🛡️ sec vuln in user val()
Example 2: Build Status
**Normal Mode (112 chars)**
Build process completed successfully. Tests are currently running, followed by deployment.
**Token Efficient (35 chars)**
build ✅ » test 🔄 » deploy ⏳
Example 3: Performance Analysis
**Normal Mode (95 chars)**
Performance analysis revealed slow processing due to O(n²) algorithm complexity.
**Token Efficient (42 chars)**
⚡ perf: slow ∵ O(n²) → optimize to O(n)
Use Cases
✅ Effective Scenarios
- **Long debugging sessions**: Efficiently maintaining history
- **Large code reviews**: Concise analysis of many files
- **CI/CD monitoring**: Real-time status updates
- **Project progress reports**: Overview of multiple task states
- **Error tracking**: Visual representation of problem chains
❌ Scenarios to Avoid
- Explanations for beginners
- Detailed documentation creation
- Initial requirements definition
- Communication with non-technical stakeholders
Implementation Examples
Debugging Session
[14:23] breakpoint → vars: {user: null, token: expired}
[14:24] step → auth.validate() ❌
[14:25] check → token.exp < Date.now() ∴ expired
[14:26] fix → refresh() → ✅
[14:27] continue → main flow 🔄File Analysis Results
/src/auth/: 🛡️ issues × 3
/src/api/: ⚡ bottleneck in handler()
/src/db/: ✅ clean
/src/utils/: ⚠️ deprecated methods
/tests/: 🧪 coverage 78%
Project Status
Frontend: 🎨 ✅ 100%
Backend: ⚙️ 🔄 75%
Database: 🗄️ ✅ migrated
Tests: 🧪 ⚠️ 68% (target: 80%)
Deploy: 📦 ⏳ scheduled
Security: 🛡️ 🚨 1 critical
Configuration Options
// Compression levels
--uc; // Ultra Compressed: Maximum compression
--mc; // Moderate Compressed: Medium compression
--lc; // Light Compressed: Light compression
// Domain-specific
--dev; // Development-focused compression
--ops; // Operations-focused compression
--sec; // Security-focused compression
Benefits
1. **Context saving**: 30-50% token reduction 2. **Visual understanding**: Intuitive grasp through symbols 3. **Information density**: More information in the same space 4. **History retention**: Maintain longer conversation history 5. **Pattern recognition**: Easier problem detection through visual patterns
Notes
- This mode only changes **AI response style**
- **Code quality** remains unchanged
- Can switch with "explain in normal mode" as needed
- Normal mode recommended for beginners and non-technical users
Command Examples
# Enable
"Token Efficient Mode on"
"Respond concisely"
"Analyze with --uc"
# Disable
"Return to normal mode
Read more
description: 'Compress responses to reduce context usage by 30-50%. Trigger with "token efficient mode", "compress responses", "save context", "save tokens".'
Compress responses to reduce context usage by 30-50%
Reduces AI response context usage by 30-50% through compression efficiency mode.
Compress responses to reduce context usage by 30-50%
Token Efficiency Mode leverages visual symbols and abbreviation systems to compress Claude's responses. **Generated code quality and content remain unchanged**. Only the explanation method changes.
Usage
# Enable mode "Respond in Token Efficiency Mode" "--uc mode" "Concise mode"
How It Works
1. Symbol System
Logic & Flow
| Symbol | Meaning | Example | | ------ | ---------------- | ------------------------------- | | → | leads to, causes | `auth.js:45 → 🛡️ security risk` | | ⇒ | converts to | `input ⇒ validated_output` | | ← | rollback, revert | `migration ← rollback` | | ⇄ | bidirectional | `sync ⇄ remote` | | & | and, combine | `🛡️ security & ⚡ performance` | | \| | or, separator | `react\|vue\|angular` | | : | define, specify | `scope: file\|module` | | » | then, sequence | `build » test » deploy` | | ∴ | therefore | `tests ❌ ∴ code broken` | | ∵ | because | `slow ∵ O(n²) algorithm` |
Status & Progress
| Symbol | Meaning | Usage | | ------ | ----------------- | ----------------------- | | ✅ | complete, success | Task completed normally | | ❌ | failed, error | Immediate action needed | | ⚠️ | warning | Review recommended | | 🔄 | in progress | Currently active | | ⏳ | pending | Scheduled for later | | 🚨 | urgent, critical | High priority |
Technical Domains
| Symbol | Domain | Usage | | ------ | ------------- | --------------------- | | ⚡ | Performance | Speed, optimization | | 🔍 | Analysis | Search, investigation | | 🔧 | Configuration | Setup, tools | | 🛡️ | Security | Protection, safety | | 📦 | Deployment | Package, bundle | | 🎨 | Design | UI, frontend | | 🏗️ | Architecture | System structure | | 🗄️ | Database | Data persistence | | ⚙️ | Backend | Server processing | | 🧪 | Testing | Quality assurance |
2. Abbreviation System
System & Architecture
- `cfg` → configuration
- `impl` → implementation
- `arch` → architecture
- `perf` → performance
- `ops` → operations
- `env` → environment
Development Process
- `req` → requirements
- `deps` → dependencies
- `val` → validation
- `auth` → authentication
- `docs` → documentation
- `std` → standards
Quality & Analysis
- `qual` → quality
- `sec` → security
- `err` → error
- `rec` → recovery
- `sev` → severity
- `opt` → optimization
Example Comparisons
Example 1: Error Report
**Normal Mode (85 chars)**
Security vulnerability found in the user validation function at line 45 of the auth system.
**Token Efficient (39 chars)**
auth.js:45 → 🛡️ sec vuln in user val()
Example 2: Build Status
**Normal Mode (112 chars)**
Build process completed successfully. Tests are currently running, followed by deployment.
**Token Efficient (35 chars)**
build ✅ » test 🔄 » deploy ⏳
Example 3: Performance Analysis
**Normal Mode (95 chars)**
Performance analysis revealed slow processing due to O(n²) algorithm complexity.
**Token Efficient (42 chars)**
⚡ perf: slow ∵ O(n²) → optimize to O(n)
Use Cases
✅ Effective Scenarios
- **Long debugging sessions**: Efficiently maintaining history
- **Large code reviews**: Concise analysis of many files
- **CI/CD monitoring**: Real-time status updates
- **Project progress reports**: Overview of multiple task states
- **Error tracking**: Visual representation of problem chains
❌ Scenarios to Avoid
- Explanations for beginners
- Detailed documentation creation
- Initial requirements definition
- Communication with non-technical stakeholders
Implementation Examples
Debugging Session
[14:23] breakpoint → vars: {user: null, token: expired}
[14:24] step → auth.validate() ❌
[14:25] check → token.exp < Date.now() ∴ expired
[14:26] fix → refresh() → ✅
[14:27] continue → main flow 🔄File Analysis Results
/src/auth/: 🛡️ issues × 3 /src/api/: ⚡ bottleneck in handler() /src/db/: ✅ clean /src/utils/: ⚠️ deprecated methods /tests/: 🧪 coverage 78%
Project Status
Frontend: 🎨 ✅ 100% Backend: ⚙️ 🔄 75% Database: 🗄️ ✅ migrated Tests: 🧪 ⚠️ 68% (target: 80%) Deploy: 📦 ⏳ scheduled Security: 🛡️ 🚨 1 critical
Configuration Options
// Compression levels --uc; // Ultra Compressed: Maximum compression --mc; // Moderate Compressed: Medium compression --lc; // Light Compressed: Light compression // Domain-specific --dev; // Development-focused compression --ops; // Operations-focused compression --sec; // Security-focused compression
Benefits
1. **Context saving**: 30-50% token reduction 2. **Visual understanding**: Intuitive grasp through symbols 3. **Information density**: More information in the same space 4. **History retention**: Maintain longer conversation history 5. **Pattern recognition**: Easier problem detection through visual patterns
Notes
- This mode only changes **AI response style**
- **Code quality** remains unchanged
- Can switch with "explain in normal mode" as needed
- Normal mode recommended for beginners and non-technical users
Command Examples
# Enable "Token Efficient Mode on" "Respond concisely" "Analyze with --uc" # Disable "Return to normal mode
A collection of commands, roles, and automation scripts for Claude Code. Automate your workflow without unnecessary confirmations, allowing you to focus on what matters.
Repo: wasabeef/claude-code-cookbook
Other skills on claude-code-cookbook.
- /analyze-dependencies
Analyze project dependencies and evaluate architectural health. Trigger with "analyze dependencies", "detect circular dependencies", "architecture issues?", "check module coupling", "find layer violations". Generates dependency matrix, fan-in/fan-out analysis, and prioritized
Open skill - /analyze-performance
Performance analysis based on Core Web Vitals with UX scoring. Trigger with "analyze performance", "improve speed", "check Core Web Vitals", "page speed", "improve LCP", "identify performance issues".
Open skill - /check-fact
Verify information accuracy against codebase and documentation. Trigger with "is this correct?", "fact check", "verify this", "is this accurate?".
Open skill - /check-prompt
Evaluate and improve AI prompt quality. Trigger with "check this prompt", "evaluate prompt quality", "improve this prompt".
Open skill - /commit-message
Generate commit messages from staged changes. Trigger with "suggest commit message", "generate commit message", "what should the commit say?", "write commit message".
Open skill - /context7
Search technical documentation via Context7 MCP. Trigger with "check the docs", "look up documentation", "how to use this library?", "API reference".
Open skill

