Skip to main content
skill CX Codex

token-efficiency · rohitg00 — Claude Code skill: what it does, how to install

token-efficiency cuts conversational fluff, caps tool executions per task, and stops Claude Code from repeatedly editing working implementations.

MIT ★ 2,966 updated 2026-09-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflow
Open on GitHub

What token-efficiency does

This skill strips conversational filler that inflates token usage. It removes apologetic disclaimers, sycophantic openers, and unrequested suggestions so Claude Code delivers direct answers or clean code immediately. All output is forced into standard ASCII characters to avoid smart quotes and unicode clutter.

Operation relies on distinct profiles for coding, data analysis, and agent workflows alongside tiered tool budgets. A small feature gets a ceiling of 50 tool calls, while research is capped at 30. A strict one-pass rule requires reading related files and test assertions first, writing the complete solution, running tests once, and stopping immediately when tests pass.

The rule prohibiting refactoring on passing code prevents spontaneous rewrites, meaning secondary cleanups require an explicit prompt.

What it helps with

  • trim conversational filler and AI disclaimers from responses
  • enforce tool-call limits according to task complexity
  • stop redundant iteration loops on code that already passes tests
  • prevent writing or modifying files without reading them first

Example prompts for the agent

  • Fix the token expiration bug in auth.ts following the token-efficiency rules.
  • Generate the summary table for test coverage using the analysis profile.
  • Implement the parser in parser.ts in a single pass based on assertions in parser.test.ts.

How to install token-efficiency

1Plugin marketplace

/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflow

This installs the whole pro-workflow plugin with all its skills

2Skills CLI (Vercel)

npx skills add rohitg00/pro-workflow --skill token-efficiency -a claude-code

3Manually: 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?

Add the marketplace source by running /plugin marketplace add rohitg00/pro-workflow, then run /plugin install pro-workflow@pro-workflow. Alternatively, install it with npx skills add rohitg00/pro-workflow --skill token-efficiency -a claude-code.

What does token-efficiency do?

It enforces direct answers without filler phrases, restricts file edits to files already inspected, and sets tool-call limits between 20 and 80 calls depending on task scope.

What is the one-pass coding discipline in this skill?

Claude Code reads existing tests first, writes the implementation once, verifies test results, and immediately halts once the test suite passes without refactoring.

Source text

SKILL.md · MIT
---
name: token-efficiency
description: Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement. Inspired by drona23/claude-token-efficient.
---

# Token Efficiency

Reduce output token waste and prevent iteration cycles that consume context.

## Trigger

Use when:
- Sessions feel expensive or slow
- Output is verbose with filler text
- Claude is re-reading files or iterating unnecessarily
- Setting up a new project for token-efficient work

## Anti-Sycophancy Rules

These patterns waste 30-60% of output tokens:

| Pattern | Example | Fix |
|---------|---------|-----|
| Sycophantic opener | "Sure! Great question!" | Delete. Lead with answer. |
| Prompt restatement | "You're asking about X..." | Delete. Answer directly. |
| Closing fluff | "Let me know if you need anything!" | Delete. Stop after the answer. |
| Unsolicited suggestions | "You might also want to..." | Delete unless asked. |
| AI disclaimers | "As an AI model..." | Delete entirely. |
| Verbose preambles | "I'll help you with that..." | Delete. Start with the action. |

## Tool-Call Budgets

Set explicit budgets by task complexity:

| Task Type | Tool-Call Budget | Wrap-Up At |
|-----------|-----------------|------------|
| Quick fix / lookup | 20 calls | 15 |
| Bug fix | 30 calls | 25 |
| Feature (small) | 50 calls | 40 |
| Feature (large) | 80 calls | 65 |
| Refactor | 50 calls | 40 |
| Exploration / research | 30 calls | 25 |

At the wrap-up threshold: commit progress, assess remaining work, decide whether to continue or start fresh.

## One-Pass Coding Discipline

For simple-to-medium tasks:

1. **Read all relevant files** including tests first
2. **Understand what tests assert** before coding
3. **Write complete solution in one pass** — not incrementally
4. **Run tests once** — if pass, STOP immediately
5. **If fail**: read the error, fix once, retest
6. **Never iterate** more than twice on the same failure — rethink approach
7. **Never refactor, improve, or polish passing code**

## Task Profiles

Switch profiles based on what you're doing:

### Coding Profile
- Return code first, explanation after (only if non-obvious)
- Simplest working solution, no over-engineering
- Read file before modifying — always
- No docstrings on unchanged code
- No error handling for impossible scenarios
- State bug, show fix, stop

### Agent/Pipeline Profile
- Structured output only: JSON, bullets, tables
- No prose unless targeting a human reader
- Every output must be parseable without post-processing
- Execute task, do not narrate actions
- Never invent file paths, API endpoints, or function names
- If unknown: return null or "UNKNOWN", never guess

### Analysis Profile
- Lead with finding, context and methodology after
- Tables and bullets over prose
- Numbers must include units
- Never fabricate data points
- Summary first (3 bullets max), caveats last

## Read-Before-Write Enforcement

Hard rules:
1. **Never write a file you haven't read** in this session
2. **Never re-read a file** already read unless it was modified
3. **Read tests before coding** — understand what passes before writing
4. **Read error output carefully** before attempting a fix

## ASCII-Only Output

Use ASCII characters only in all output:
- `--` not `—` (em dash)
- `"` not `"` `"` (smart quotes)
- `'` not `'` `'` (curly apostrophes)
- No emoji unless explicitly requested
- No Unicode decorators or special characters

This ensures clean copy-paste for code and compatibility with downstream systems.

## Measuring Impact

Track these metrics to measure token savings:
- **Output length**: average words per response (target: 30-50% reduction)
- **Tool calls per task**: should stay within budget tier
- **Re-read count**: should be near zero
- **Write-without-read count**: should be zero
- **Iteration cycles**: tests should pass in 1-2 attempts, not 5+

## Attribution

Token efficiency patterns adapted from [drona23/claude-token-efficient](https://github.com/drona23/claude-token-efficient) (MIT).

© Rohit Ghumare · MIT · rohitg00/pro-workflow

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 NickCrew 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. CX Codex +1 245installs 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-check egorfedorov token-check estimates token usage for snippets, files, or chat history. Shows how context limits are consumed and suggests ways to trim the prompt. CX Codex +1 ★ 134repo stars 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 alexgreensh token-optimizer — a skill for Claude Code and Codex that tracks where the context window goes, suggests fixes, and applies the ones you approve. Kick it off when sessions feel tight or the bill starts climbing. CX Codex +1 1,100installs token-optimization claude-dev-suite token-optimization teaches agents to minimize token usage when calling MCP tools and external APIs. Keeps context clean by enforcing limits and compact responses. CX Codex +1 354installs fable-baton realgarit fable-baton turns Fable 5 into an orchestrator in Claude Code, routing implementation to tiered Opus, Sonnet, and Haiku subagents. ★ 1,013repo stars claude-hud-statusline reason-machines claude-hud-statusline keeps a status line under your prompt showing how full the context window is, which tools and subagents are running, and how far the todo list has got. CX Codex +1 2,700installs

From the same set83

The whole set →
bug-capture bug-capture is a Claude Code skill that turns reported defects into GitHub issues using the project’s own terms. It activates after a conversational bug report, a QA pass, or a request to file an issue. CX Codex +1 ★ 2,966repo stars context-optimizer context-optimizer controls token consumption and frees context in Claude Code. Use it when agent sessions slow down, forget instructions, or approach budget limits. CX Codex +1 ★ 2,966repo stars deslop deslop trims unnecessary code from the current branch diff and checks SKILL.md files. Run it before committing or reviewing a skill for release. CX Codex +1 ★ 2,966repo stars wiki-builder wiki-builder is a Claude Code skill that creates a structured knowledge base from Markdown pages and an FTS5 index in SQLite. It persists between sessions and is queryable by the agent. CX Codex +1 ★ 2,966repo stars wiki wiki is a Claude Code command that builds and maintains persistent research wikis. It stores markdown files, indexes them in SQLite FTS5, and retrieves context via BM25. CX Codex +1 ★ 2,966repo stars wiki-viewer wiki-viewer writes a pro-workflow wiki out as a single HTML file with pages, sources, claims, a seed queue, a link graph and search. Useful for handing research state to someone else. CX Codex +1 ★ 2,966repo stars llm-council llm-council runs multi-model deliberation in three stages: parallel drafts, anonymous peer rankings, and final synthesis by a designated chairman. CX Codex +1 ★ 2,966repo stars design-engineering The design-engineering skill guides interface animation choices and UI reviews. Use it when refining a component, transition, modal, or other interactive state. CX Codex +1 ★ 2,966repo stars

Project sponsors

Companies that keep this analytics open