Reduce Token

Activates compact, high-density response mode when the user types `/reduceToken` or any variant like `/reduceToken 500` or `/reduceToken study`. Apply this skill immediately and hold it for the entire session. Trigger on: `/reduceToken`, "token constraint", "reduce tokens", "compact mode", "token budget reminder", or when the user pastes a disclaimer about token limits. Do not wait to be asked twice — activate on first signal and confirm with a single line.

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add sham-jadhav03/Claude_Skills --skill reduce-token
Manual install
git clone --depth 1 https://github.com/sham-jadhav03/Claude_Skills.git /tmp/Claude_Skills
mkdir -p ~/.claude/skills
cp -r /tmp/Claude_Skills/reduce-token ~/.claude/skills/reduce-token

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

From the SKILL.md

# /reduceToken Skill

## Activation

Triggers on:
- `/reduceToken` — activates with default 300–800 token budget
- `/reduceToken [N]` — overrides budget to N tokens for this session
- `/reduceToken study` — activates Study Mode (see below)
- `/reduceToken off` — deactivates; returns to default response style

On activation, reply with exactly one line:
> `✓ reduceToken active — [budget] token target. Rules applied for this session.`

Then immediately begin the task if one was given alongside the command.

---

## Core Constraint (read this first)

**Never sacrifice correctness, completeness, or critical risks to reduce token count.**

Token reduction is a style constraint, not a quality constraint. A wrong answer in 200 tokens is worse than a correct answer in 900.

---

## Primary Goal

Maximize information density. Minimize token usage.
The objective is **the best solution per token** — not the shortest answer.

---

## Output Rules

- Never repeat the user's request
- Never explain what you are about to do
- Never add introductions or conclusions
- Never use filler text
- Never restate obvious information
- Prefer bullets over prose
- Prefer tables over long explanations
- Prefer examples over theory
- Prefer diffs over full rewrites
- Prefer implementation over discussion
- Apply these rules to every response in this session

---

## Coding Rules

- Output only the necessary code
- Explain only non-obvious decisions
- Do not regenerate unchanged files
Read the full skill on GitHub

Details

Skill name
reduce-token
Path
reduce-token/SKILL.md
License
MIT
Repo updated
25 October 2026

FAQ

What does the Reduce Token skill do?

Activates compact, high-density response mode when the user types `/reduceToken` or any variant like `/reduceToken 500` or `/reduceToken study`. Apply this skill immediately and hold it for the entire session. Trigger on: `/reduceToken`, "token constraint", "reduce tokens", "compact mode", "token budget reminder", or when the user pastes a disclaimer about token limits. Do not wait to be asked twice — activate on first signal and confirm with a single line.

How do I install the Reduce Token skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add sham-jadhav03/Claude_Skills --skill reduce-token. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Reduce Token popular?

It lives in sham-jadhav03/Claude_Skills, which has 5 GitHub stars and 0 forks.

Related skills

Oa

5

sham-jadhav03/Claude_Skills

Activates Deep Problem Solver mode when the user types `/oa`. Applies a strict 7-phase framework: Understand → Trap Hunt → Model → Plan → Execute → Verify → Answer. Use for DSA problems, algorithm questions, coding interviews, and any problem where pattern-matching leads to wrong answers. Never skip Phase 1 or Phase 2. Never jump to code before both are complete.

Software Development

Cheat Learn From

9

miaqu766520-a11y/ai-line-skills

从对标账号导入 script + 数据 → 拆 pattern + 派生 base rubric 信号 → 写到 benchmark.md / script_patterns.md / rubric_notes.md。**这是工具最早期信号的来源**——cold-start 用户没自己历史时全靠对标,发过历史的用户也建议至少 1 个对标做 sanity check。触发词:"学这个账号"/"拆这几个对标视频"/"learn from"/"导入对标账号"/"找对标"。

Learning & Education

Noise Emulate

9

pasqal-io/agent-marketplace

Emulate a neutral-atom Pulser sequence's time evolution under the target Rydberg device's live noise model, producing noiseless and noisy trajectory curves with a quantile envelope. Asks where to run — this machine, a GPU cluster, or Pasqal Cloud emulators. Use this to study how noise shapes a signal over time; use validate-emu to decide whether an experiment is worth submitting. Triggered by phrases like "run a noise emulation of this sequence", "emu-mps with noise", "noise envelope".

Learning & Education

Navigating

9

yasunori0418/skills

Navigate the user through reading code stop by stop to pay down understanding debt left by AI tooling. Explicit invocation only.

Learning & Education

Onboarding Teardown

9

adaptyteam/adapty-skills

Use when someone wants to improve, fix, test or critique a mobile app's onboarding — "here's my onboarding", "roast my flow", "why do users drop off before the paywall", a competitor's signup flow, a welcome or activation flow, a quiz, or a flow described in one sentence. Also use whenever YOU are the one designing or generating an onboarding sequence and were given no design reference to follow — no reference screens, no existing flow to copy, no spelled-out sequence — as in "build me an onboarding", "add a quiz before the paywall", "make a flow that converts"; this library is the reference i

Learning & Education

Quizzing

9

yasunori0418/skills

Quiz the user on a plan, implementation, or codebase to pay down understanding debt left by AI tooling. Explicit invocation only.

Learning & Education

Browse the most popular Claude skills, all learning & education skills, or write your own with the skills generator.