Agent skill

Token Efficiency

Cross-platform token audit and optimization for AI coding agents (Cursor, Codex, Claude Code, Hermes, Windsurf, Cline, OpenClaw, Gemini CLI, Aider).

Apache-2.0Auto-check passedAgent Workflows

Install Token Efficiency

skills CLI

$ npx skills add HHU3637kr/skills --skill token-efficiency -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install HHU3637kr/skills token-efficiency --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/HHU3637kr/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/token-efficiency .claude/skills/token-efficiency && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "token-efficiency" agent skill from https://github.com/HHU3637kr/skills/tree/master/token-efficiency into .claude/skills/token-efficiency/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-efficiency", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/HHU3637kr/skills/tree/master/token-efficiency

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add HHU3637kr/skills --skill token-efficiency -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install HHU3637kr/skills token-efficiency --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HHU3637kr/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/token-efficiency .agents/skills/token-efficiency && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "token-efficiency" agent skill from https://github.com/HHU3637kr/skills/tree/master/token-efficiency into .agents/skills/token-efficiency/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-efficiency", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add HHU3637kr/skills --skill token-efficiency -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install HHU3637kr/skills token-efficiency --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HHU3637kr/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/token-efficiency .cursor/skills/token-efficiency && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "token-efficiency" agent skill from https://github.com/HHU3637kr/skills/tree/master/token-efficiency into .cursor/skills/token-efficiency/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-efficiency", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/HHU3637kr/skills.git --path token-efficiency

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add HHU3637kr/skills --skill token-efficiency -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install HHU3637kr/skills token-efficiency --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HHU3637kr/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/token-efficiency .gemini/skills/token-efficiency && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "token-efficiency" agent skill from https://github.com/HHU3637kr/skills/tree/master/token-efficiency into .gemini/skills/token-efficiency/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-efficiency", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install HHU3637kr/skills token-efficiency

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add HHU3637kr/skills --skill token-efficiency -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/HHU3637kr/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/token-efficiency .github/skills/token-efficiency && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "token-efficiency" agent skill from https://github.com/HHU3637kr/skills/tree/master/token-efficiency into .github/skills/token-efficiency/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-efficiency", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add HHU3637kr/skills --skill token-efficiency -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install HHU3637kr/skills token-efficiency --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HHU3637kr/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/token-efficiency .opencode/skills/token-efficiency && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "token-efficiency" agent skill from https://github.com/HHU3637kr/skills/tree/master/token-efficiency into .opencode/skills/token-efficiency/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-efficiency", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: token-efficiency
GitHub stars: 145
Token cost: ~842 tokens
SKILL.md length: 226 words
Files: 57 (incl. scripts, references)
Skills in repo: 37
Repo updated: Sep 23, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Cross-platform token audit and optimization for AI coding agents (Cursor, Codex, Claude Code, Hermes, Windsurf, Cline, OpenClaw, Gemini CLI, Aider).

Works in 4 steps: AUDIT — scripts/audit.py → fixed tax +… → FIX L0 — MCP prune, skill on-demand,… → FIX L1/L2/L3 — scripts/install.py →… → …
Reduce API cost
SKILL.md covers 学员 / 讲师, Quick commands, Workflow and Six layers, plus 3 more sections
Calls python3 and bash

What it does

Token Efficiency is an agent skill from HHU3637kr/skills. Cross-platform token audit and optimization for AI coding agents (Cursor, Codex, Claude Code, Hermes, Windsurf, Cline, OpenClaw, Gemini CLI, Aider). Scans always-on context, MCP tools, skills; ranks ROI fixes; installs L0-L3 rules; shrinks large tool outputs. Use for save tokens, token audit, context bloat, MCP prune, reduce API cost, agent efficiency, payload shrink.

Its SKILL.md is about 840 tokens, which your agent loads only when the skill is triggered. The skill folder holds 60 other files, including scripts and reference files (for example `AGENT_INSTALL.md`, `README.md` and `START_HERE.md`).

It sits in Agent Workflows, covering MCP servers. It works with Model Context Protocol. The licence is Apache-2.0.

When your agent uses it

Reduce API cost
Agent efficiency

Example prompts

“/token-efficiency”

Requirements

Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

AUDIT — scripts/audit.py → fixed tax + duplicates + ROI fixes
FIX L0 — MCP prune, skill on-demand, compress, dedup
FIX L1/L2/L3 — scripts/install.py → behavior + payload + output + capability guardrails
VERIFY — scripts/perf.py --compare-baseline or re-run audit

What it can do on your machine

Read from SKILL.md and the folder at commit a2cccf6. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
- python3
- bash
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Token Efficiency loads about 842 tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 226 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~97
When it runs · the whole SKILL.md, loaded when a task matches: ~842
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from HHU3637kr/skills at commit a2cccf6, republished under its Apache-2.0 licence (© HHU3637kr). 226 words, ~842 tokens.

Download SKILL.mdSave it as .claude/skills/token-efficiency/SKILL.md (or your agent's skills folder). This skill also uses 56 other files; get the full folder from GitHub.

name: token-efficiency
description: Cross-platform token audit and optimization for AI coding agents (Cursor, Codex, Claude Code, Hermes, Windsurf, Cline, OpenClaw, Gemini CLI, Aider). Scans always-on context, MCP tools, skills; ranks ROI fixes; installs L0-L3 rules; shrinks large tool outputs. Use for save tokens, token audit, context bloat, MCP prune, reduce API cost, agent efficiency, payload shrink.
disable-model-invocation: true

Token Efficiency v0.3.1

Prime directive: Audit before adding rules. Rules are fixed tax too.

Capability promise: Save waste, not intelligence. Guardrails ship with every rule install.

学员 / 讲师

bash

# 讲师打包
python3 scripts/package_release.py   # → dist/token-efficiency-0.3.1.zip

# 学员解压后
bash install.sh
python3 scripts/setup_student.py

文档：docs/学员安装指南.md · docs/能力保障说明.md · docs/架构说明.md

Quick commands

bash

# Install skill globally (once)
bash install.sh
# or: python3 scripts/install_skill.py --write

# Audit + optional ledger
python3 scripts/audit.py --project . --with-ledger

# Fix auto-invoke skills (L0)
python3 scripts/fix_skills.py --list
python3 scripts/fix_skills.py --write --keep skill-a,skill-b

# Compress bloated CLAUDE.md (L0)
python3 scripts/compress.py CLAUDE.md --write

# Shrink large tool output (L2)
python3 scripts/shrink.py build.log --vault -o build.log.shrunk

# Before/after savings report
python3 scripts/perf.py --save-baseline
python3 scripts/perf.py --compare-baseline

# Install rules to project
python3 scripts/install.py --write --agents cursor,claude-code,hermes,openclaw,codex --levers 1,2,3

Windows: replace python3 with python or py -3.

Workflow

AUDIT — scripts/audit.py → fixed tax + duplicates + ROI fixes
FIX L0 — MCP prune, skill on-demand, compress, dedup
FIX L1/L2/L3 — scripts/install.py → behavior + payload + output + capability guardrails
VERIFY — scripts/perf.py --compare-baseline or re-run audit

Six layers

L	Layer	Fix tool
L0	Fixed tax	audit, compress, MCP edit
L1	Turn multiplier	install lever 1
L2	Context inflation	install lever 2 + shrink.py (+ vault restore)
L3	Output waste	install lever 3
L4	Session bloat	new chat / Ask mode — see context-design
L5	Model mismatch	user picks tier — see context-design

Details: taxonomy.md

Supported agents

cursor · claude-code · codex · hermes · openclaw · windsurf · cline · aider · continue · gemini · generic

Matrix: references/agent-matrix.md

References

capabilities.md — full feature stack
platform-notes.md — Win/Mac/Linux/WSL
design-principles.md — architecture notes

Agent execution rules (when this skill is active)

Run audit before proposing new always-on rules
Present top 3 ROI fixes with layer tags
One lever at a time unless user asks batch
Never let efficiency block correct task completion — see capability-guardrails.md
Use shrink.py with --vault for tool output > ~4K est. tokens; restore if detail missing
Honor user overrides: 详细解释 / explore freely / run tests / 看完整日志
Never claim exact dollar savings without user's pricing data

Files

SKILL.md and 56 other files (scripts, references) in token-efficiency of HHU3637kr/skills.

SKILL.md
.gitignore
AGENT_INSTALL.md
LICENSE
README.md
START_HERE.md
VERSION
adapters/claude-code/AGENTS-behavior.snippet.md
adapters/claude-code/AGENTS-output.snippet.md
adapters/claude-code/CLAUDE.snippet.md
adapters/claude-code/README.md
adapters/codex/README.md
adapters/codex/SKILL.snippet.md
adapters/cursor/token-efficiency-behavior.mdc
adapters/cursor/token-efficiency-context.mdc
adapters/cursor/token-efficiency-output.mdc
adapters/generic
… and 40 more

Open the folder on GitHubat commit a2cccf6

Compare with similar skills

Token Efficiency next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Token Efficiency compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Token Efficiency this skillHHU3637kr/skills	145	—	~842	Automated safety check: Pass	Apache-2.0	15 days ago
MCP Server Builderanthropics/skills	180k	64 repos	~2.3k	Automated safety check: Pass	Apache-2.0	2 days ago
MCP Server BuildershareAI-lab/learn-claude-code	78k	5 repos	~1.2k	Automated safety check: Pass	MIT	9 days ago
MCP Integration for Pluginsanthropics/claude-plugins-official	38k	11 repos	~3.1k	Automated safety check: Pass	Apache-2.0	today
Fastmcp Client CLIPrefectHQ/fastmcp	28k	1 repos	~823	Automated safety check: Pass	Apache-2.0	today
Crush Configurationcharmbracelet/crush	29k	—	~3.7k	Automated safety check: Pass	Custom licence	today

Similar skills

MCP Server Builder
anthropics/skills
Official
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
180k GitHub starsUsed in 64 repos~2.3k tokens
Agent WorkflowsAuto-check passed
MCP Server Builder
shareAI-lab/learn-claude-code
Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.
78k GitHub starsUsed in 5 repos~1.2k tokens
Agent WorkflowsAuto-check passed
MCP Integration for Plugins
anthropics/claude-plugins-official
Official
Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.
38k GitHub starsUsed in 11 repos~3.1k tokens
Agent WorkflowsAuto-check passed
Fastmcp Client CLI
PrefectHQ/fastmcp
Query and invoke tools on MCP servers using fastmcp list and fastmcp call.
28k GitHub starsUsed in 1 repo~823 tokens
Agent WorkflowsAuto-check passed
Crush Configuration
charmbracelet/crush
Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.
29k GitHub stars~3.7k tokensUpdated today
Agent WorkflowsAuto-check passed
Context Mode Output Sandbox
mksglu/context-mode
Routes large command, file, API and browser output through context-mode tools so only the needed result enters the agent's context, instead of dumping it via Bash.
26k GitHub stars~4.1k tokensUpdated today
Agent WorkflowsAuto-check passed

Questions about Token Efficiency

What does Token Efficiency do?

Cross-platform token audit and optimization for AI coding agents (Cursor, Codex, Claude Code, Hermes, Windsurf, Cline, OpenClaw, Gemini CLI, Aider). Token Efficiency is an agent skill from HHU3637kr/skills. Cross-platform token audit and optimization for AI coding agents (Cursor, Codex, Claude Code, Hermes, Windsurf, Cline, OpenClaw, Gemini CLI, Aider).

When should I use Token Efficiency?

Token Efficiency fits situations like: reduce API cost; agent efficiency.

How do I install Token Efficiency in Claude Code?

Run `npx skills add HHU3637kr/skills --skill token-efficiency -a claude-code`. Or copy the skill folder (token-efficiency in HHU3637kr/skills) into .claude/skills/token-efficiency in your project. Claude Code loads it when a task matches its description.

How do I install Token Efficiency in Codex?

Run `npx skills add HHU3637kr/skills --skill token-efficiency -a codex`. Or copy the skill folder (token-efficiency in HHU3637kr/skills) into .agents/skills/token-efficiency in your project. Codex loads it when a task matches its description.

Can I use Token Efficiency in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HHU3637kr/skills --skill token-efficiency -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/token-efficiency, .gemini/skills/token-efficiency, .github/skills/token-efficiency and .opencode/skills/token-efficiency in your project.

What does Token Efficiency need to run?

Going by SKILL.md and its folder, Token Efficiency needs the command-line tools its instructions call (python3 and bash). Our summary lists: Python 3.

Does Token Efficiency access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Token Efficiency safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Token Efficiency use?

Token Efficiency is published under the Apache-2.0 licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Token Efficiency use?

About 842 tokens (SKILL.md is roughly 3.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 954 tokens, read only when the agent opens those files.

What are the alternatives to Token Efficiency?

Skills that share tags, products or a category with Token Efficiency: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Token Efficiency?

HHU3637kr (a GitHub user) maintains it in HHU3637kr/skills, which has 145 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on September 23, 2026.

Source: HHU3637kr/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Token Efficiency

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Token Efficiency v0.3.1

学员 / 讲师

Quick commands

Workflow

Six layers

Supported agents

References

Agent execution rules (when this skill is active)

Files

Compare with similar skills

Similar skills

More from HHU3637kr/skills

Related

Questions about Token Efficiency