nowait-reasoning-optimizer

nowait-reasoning-optimizer is a skill for Claude Code, Codex from foryourhealth111-pixel/Vibe-Skills. It costs 110 tokens per session (1,257 once invoked), scanned A, original, Apache-2.0.

An inference-time method for reducing the self-reflection text produced by reasoning-focused language models such as DeepSeek-R1 and Qwen3. It suppresses tokens like “Wait” and “Alternatively” while the model generates an answer.

In plain words
What is it for?
Use it when deploying supported reasoning models and trying to reduce inference cost or latency without retraining the model.
Why use it?
It shortens reasoning traces, which can reduce response time and token use. It also warns that this approach can reduce performance on some smaller distilled models.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when deploying supported reasoning models and trying to reduce inference cost or latency without retraining the model.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/foryourhealth111-pixel/vibe-skills/nowait-reasoning-optimizer
About the project

Vibe-Skills is a collection and routing system that helps AI agents discover, select, and coordinate specialized skills for completing tasks. It is intended for agents that need to organize workflows across many installed capabilities. The catalogue entries are skills and an agent belonging to this system.

foryourhealth111-pixel/Vibe-Skills · 3,252 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add foryourhealth111-pixel/Vibe-Skills --skill nowait-reasoning-optimizer
Clone the repo
git clone --depth 1 https://github.com/foryourhealth111-pixel/Vibe-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for nowait-reasoning-optimizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/foryourhealth111-pixel/vibe-skills/nowait-reasoning-optimizer/github.svg)](https://agentmods.dev/skills/foryourhealth111-pixel/vibe-skills/nowait-reasoning-optimizer)
Your own site
<a href="https://agentmods.dev/skills/foryourhealth111-pixel/vibe-skills/nowait-reasoning-optimizer"><img src="https://agentmods.dev/badge/skills/foryourhealth111-pixel/vibe-skills/nowait-reasoning-optimizer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for nowait-reasoning-optimizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/foryourhealth111-pixel/vibe-skills/nowait-reasoning-optimizer"><img src="https://agentmods.dev/badge/skills/foryourhealth111-pixel/vibe-skills/nowait-reasoning-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,257 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.01257
Opus 5 $0.00055 $0.00629
Sonnet 5 $0.00022 $0.00251
Haiku 4.5 $0.00011 $0.00126

Measured 9d ago against content hash fd71e79f3601, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

nowait-reasoning-optimizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/nowait_processor.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

bundled/skills/nowait-reasoning-optimizer/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NOWAIT Reasoning Optimizer

Implements the NOWAIT technique from the paper "Wait, We Don't Need to 'Wait'! Removing Thinking Tokens Improves Reasoning Efficiency" (Wang et al., 2025).

Overview

NOWAIT is a training-free inference-time intervention that suppresses self-reflection tokens (e.g., "Wait", "Hmm", "Alternatively") during generation, reducing chain-of-thought (CoT) trajectory length by 27-51% without compromising model utility.

When to Use

  • Deploying R1-style reasoning models with limited compute
  • Reducing inference latency for production systems
  • Optimizing token costs for reasoning tasks
  • Working with verbose CoT outputs that need streamlining

Supported Models

Model Series Type Token Reduction
QwQ-32B RL-based 16-31%
Phi4-Reasoning-Plus RL-based 23-28%
Qwen3-32B RL-based 13-16%
Kimi-VL-A3B Multimodal 40-60%
QvQ-72B-Preview Multimodal 20-30%

Important: NOWAIT works best with RL-based models. Distilled models (Qwen3-4B/8B/14B) show degraded performance when reflection tokens are suppressed.

Quick Start

1. Basic Implementation

from scripts.nowait_processor import NOWAITLogitProcessor

# Initialize processor for your model's tokenizer
processor = NOWAITLogitProcessor(tokenizer)

# Use during generation
outputs = model.generate(
    inputs,
    logits_processor=[processor],
    max_new_tokens=32768
)

2. Keywords Suppressed

See references/keywords.md for the complete list. Core keywords:

wait, alternatively, hmm, but, however, check, 
double-check, maybe, verify, again, oh, ah

How It Works

  1. Initialize Keywords: Identify reflection keywords from empirical analysis
  2. Expand to Token Variants: Map keywords to all token variants in vocabulary (e.g., "wait" → " wait", "Wait", " Wait", ".wait", "WAIT")
  3. Suppress During Inference: Set logits of reflection tokens to large negative values during decoding

Read the full file on GitHub · 146 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 146 lines · 110 tokens per session scan A fd71e79f3601

Subscribe to this mod's changes

nowait-reasoning-optimizer is a skill published in the GitHub repository foryourhealth111-pixel/Vibe-Skills (3,252 stars, last pushed 12d ago), licensed Apache-2.0. It adds 110 tokens to every session and 1,257 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

ai-orchestration-langchain

LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing.

agents-inc/skills · 43 tokens

ai-observability-promptfoo

Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation.

agents-inc/skills · 46 tokens

guidance

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.

braxtonROSE4/zorro-agent · 38 tokens

godmode

Jailbreak API-served LLMs using G0DM0D3 techniques — Parseltongue input obfuscation (33 techniques), GODMODE CLASSIC system prompt templates, ULTRAPLINIAN multi-model racing, encoding escalation, and Zorro-native prefill/system prompt integration. Use when a user wants to bypass safety filters, jailbreak a model, or…

braxtonROSE4/zorro-agent · 83 tokens

prompt-engineer

Prompt engineering expert for chain-of-thought, few-shot learning, evaluation, and LLM optimization.

RightNow-AI/openfang · 23 tokens

happyhorse-prompt-studio

Interactive prompt studio for HappyHorse 1.0 video generation. Guides users through scenario discovery with vivid examples, then assembles production-ready prompts in JP/CN/EN. Use when someone wants to create AI video content with HappyHorse but doesn't know where to start, or when they have a specific scenario and…

modelstudioai/skills · 93 tokens