agentmods.dev

lightcompress-quant-explore

lightcompress-quant-explore is a skill for Claude Code, Codex from HorizonRobotics/OE-Skills. It costs 42 tokens per session (1,312 once invoked), scanned A, original, Apache-2.0.

A workflow for running LightCompress model-quantization experiments and producing accuracy reports. Quantization reduces the numerical precision used by a machine-learning model to explore smaller or faster versions.

In plain words
What is it for?
Use it to prepare and run quantization tests, evaluate perplexity (a measure of language-model prediction quality), inspect YAML settings, and save accuracy results when the cache is available.
Why use it?
It organizes experiment setup, user confirmation, execution, and result caching in a repeatable process.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: names the AskUserQuestion tool.

not rated 27repo 4mo ago A scan 42 tokens original Apache-2.0

Good fit Use it to prepare and run quantization tests, evaluate perplexity (a measure of language-model prediction quality), inspect YAML settings, and save accuracy results when the cache is available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/horizonrobotics/oe-skills/lightcompress-quant-explore
View source ↗ HorizonRobotics/OE-Skills
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 HorizonRobotics/OE-Skills --skill lightcompress-quant-explore
Clone the repo
git clone --depth 1 https://github.com/HorizonRobotics/OE-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 lightcompress-quant-explore

README.md
[![agentmods](https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/lightcompress-quant-explore/github.svg)](https://agentmods.dev/skills/horizonrobotics/oe-skills/lightcompress-quant-explore)
Your own site
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/lightcompress-quant-explore"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/lightcompress-quant-explore/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 lightcompress-quant-explore

Your own site · 80×15
<a href="https://agentmods.dev/skills/horizonrobotics/oe-skills/lightcompress-quant-explore"><img src="https://agentmods.dev/badge/skills/horizonrobotics/oe-skills/lightcompress-quant-explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,312 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.
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 $0.00042 $0.01312
Opus 5.5 $0.00017 $0.00525
Sonnet 5.5 $0.00008 $0.00262
Haiku 4.5 $0.00004 $0.00131

Measured 2mo ago against content hash ef83d7504983, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lightcompress-quant-explore 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 2mo ago.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/execute_experiment.py, scripts/lib/__init__.py, scripts/lib/config.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.

horizon/skills/llm/lightcompress/lightcompress-quant-explore/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LightCompress 量化探索实验

执行流程（4 阶段）

Phase 1: 准备实验

调用 prepare_experiment.py 创建实验目录和 YAML 配置：

python {skill_dir}/scripts/prepare_experiment.py \
  --model /path/to/model \
  --model-type Qwen2 \
  --method smoothquant \
  --w-bit 8 \
  --a-bit 8

注意：不指定 --workspace 时，脚本默认使用 {当前工作目录}/experiments 作为输出目录。

脚本输出 JSON 包含：

  • experiment_dir: 实验目录路径
  • config_path: YAML 配置路径
  • yaml_content: 完整 YAML 配置内容

Phase 2: 用户确认

向用户展示完整的 YAML 配置内容，让用户检查是否符合预期。

使用 AskUserQuestion 询问：开始实验 / 取消

Phase 3: 执行实验

用户确认后，调用 execute_experiment.py 执行实验：

python {skill_dir}/scripts/execute_experiment.py {experiment_dir}

Phase 4: 保存精度缓存

实验成功后，检查 <project_root>/.claude/skills/quant-accuracy-cache/ 是否存在：

  • 存在：调用 quant-accuracy-cache skill 保存结果
  • 不存在：跳过

参数说明

prepare_experiment.py 参数

参数 必需 说明 默认值
--model ✅ 模型路径 -
--model-type ✅ 模型类型 -
--method ✅ 量化方法 -
--w-bit 权重量化位宽 4
--a-bit 激活量化位宽 8
--fast-mode 快速验证模式 false
--save-artifacts 保存量化产物 false
--workspace 工作目录 ./experiments
--mix-bits 混合精度组(可多次),见下方示例 -
--special 覆盖 quant.special 参数(可多次),KEY=VAL -
--calib-path 校准数据集路径 内置 wikitext2_calib
--calib-name 校准数据集名 wikitext2
--calib-n-samples 校准样本数(显式值不被显存降级) 自动
--calib-seq-len 校准序列长度 模板默认
--calib-preproc 校准预处理 wikitext2_gptq
--eval-path 评估数据集路径 内置 wikitext2_eval
--eval-seq-len 评估序列长度 模板默认
--no-eval-pretrain 只评 fake_quant,跳过 pretrain false
--inference-per-block 逐 block 推理评测(大模型省显存) false
--save-path fakequant 保存路径(指定即开 save_fake) -

混合精度 (mix_bits) 示例

将 q/o_proj + MoE expert 设为 W4、其余 W8(Gemma4Moe 常用):

python {skill_dir}/scripts/prepare_experiment.py \
  --model /jfs-public/openexplorer_llm/models/gemma-4-26B-A4B-it \
  --model-type Gemma4Moe --method gptq --w-bit 8 --a-bit 8 \
  --mix-bits "name=qo_experts_w4;bit=4;layers=self_attn.q_proj,self_attn.o_proj,experts.experts.*.gate_proj,experts.experts.*.up_proj,experts.experts.*.down_proj" \
  --calib-n-samples 256 --calib-seq-len 1024 \
  --no-eval-pretrain --inference-per-block \
  --save-path /path/to/save/ \
  --env-activate ~/miniconda3/etc/profile.d/conda.sh

Read the full file on GitHub · 116 lines

Files

What ships with it

15 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. 2mo ago First seen · 116 lines · 42 tokens per session scan A ef83d7504983

Subscribe to this mod's changes

lightcompress-quant-explore is a skill published in the GitHub repository HorizonRobotics/OE-Skills (27 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,312 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.

Analytics and metricsData and AI
Related

lightcompress-quant-explore compared with skills from other repositories

lightcompress-quant-explore next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lightcompress-quant-exploreHorizonRobotics/OE-SkillsSkill274mo agoApache-2.0A42Claude Code, Codex
agent-platform-model-registrygoogle/skillsSkill22kyesterdayApache-2.0A60Claude Code, Codex
foundry-config-setupmicrosoft/agent-frameworkSkill15kyesterdayMITA65Claude Code, Codex
google-cloud-solution-agentic-analytics-spark-knowledge-cataloggoogle/skillsSkill22kyesterdayApache-2.0A132Claude Code, Codex
training-checkwanshuiyin/Auto-claude-code-research-in-sleepSkill19k3d agoMITA35Claude Code
nemo-automodel-launcher-configNVIDIA/skillsSkill3.9kyesterdayApache-2.0A30Claude Code
finetuningmicrosoft/skillsSkill3.2kyesterdayMITA132Claude Code