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.
npx skills add KerberosClaw/kc_ai_skills --skill llm-benchmarkgit clone --depth 1 https://github.com/KerberosClaw/kc_ai_skillsWrote 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.
[](https://agentmods.dev/skills/kerberosclaw/kc_ai_skills/llm-benchmark)<a href="https://agentmods.dev/skills/kerberosclaw/kc_ai_skills/llm-benchmark"><img src="https://agentmods.dev/badge/skills/kerberosclaw/kc_ai_skills/llm-benchmark/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.
<a href="https://agentmods.dev/skills/kerberosclaw/kc_ai_skills/llm-benchmark"><img src="https://agentmods.dev/badge/skills/kerberosclaw/kc_ai_skills/llm-benchmark.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00082 | $0.02162 |
| Opus 5 | $0.00041 | $0.01081 |
| Sonnet 5 | $0.00016 | $0.00432 |
| Haiku 4.5 | $0.00008 | $0.00216 |
Grade D, and why
llm-benchmark scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo systemctl restart ollama Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- 若 **未安裝**：執行 `curl -fsSL https://ollama.com/install.sh | sh`，再啟動服務 Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:11434/api/version 2>/dev/null || echo "NOT_RUNNING" How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM Benchmark Skill
You are a local LLM benchmarking specialist. 你負責用可重現的命令測 Ollama 模型效能，保護使用者現有服務狀態，並把推薦和限制講清楚。
不適用
- 不評測雲端 API 模型。
- 不用單次主觀聊天感覺取代 benchmark。
- 不在未確認硬體與服務狀態前直接 pull 大模型或重啟服務。
執行以下完整流程：
Step 0：環境檢查
# 確認 Ollama 是否安裝並運行
curl -s http://localhost:11434/api/version 2>/dev/null || echo "NOT_RUNNING"
which ollama 2>/dev/null || echo "NOT_INSTALLED"
- 若 未安裝：執行
curl -fsSL https://ollama.com/install.sh | sh，再啟動服務 - 若 未運行：執行
ollama serve &或systemctl start ollama - 確認成功後繼續
Step 0.5：VRAM 清空（benchmark 前必做）
1. 停止其他吃 GPU / RAM 的本地 LLM 服務（若有且正在運行）
# 檢查是否有 LLM gateway 類容器正在運行（例：OpenClaw、LM 代理服務）
LLM_GATEWAY="your-llm-gateway" # 換成你的服務名，例：openclaw
docker ps --format '{{.Names}}' | grep -i "$LLM_GATEWAY"
- 若有相關容器正在運行 → 停止它：
LLM_STACK_DIR="$HOME/your-llm-stack" # 換成你的 compose 目錄 GATEWAY_SERVICE="gateway" # 換成你的服務名 cd "$LLM_STACK_DIR" && docker compose stop "$GATEWAY_SERVICE" - 若無相關容器，或容器已停止 → 跳過此步驟
記錄該服務是否原本是啟動的，benchmark 完成後需還原狀態。
2. 重啟 Ollama 清除 VRAM（必做）
sudo systemctl restart ollama
sleep 5
3. 確認 VRAM 已釋放
nvidia-smi --query-gpu=memory.used,memory.free --format=csv,noheader,nounits
確認 memory.used 降到 ~1500 MB 以下再繼續。若仍偏高，再等 5 秒重確認。
4. Benchmark 完成後還原服務
若步驟 1 有停止服務，benchmark 全部完成後執行：
cd "$LLM_STACK_DIR" && docker compose start "$GATEWAY_SERVICE"
Step 1：取得 GPU/VRAM 資訊
nvidia-smi --query-gpu=name,memory.total,memory.free --format=csv,noheader,nounits 2>/dev/null \
|| rocm-smi --showmeminfo vram 2>/dev/null \
|| echo "NO_GPU"
依據 可用 VRAM 推薦模型最大參數量（以 Q4 量化為基準）：
| 可用 VRAM | 推薦最大 B |
|---|---|
| < 4 GB | 3B |
| 4–6 GB | 7B |
| 6–8 GB | 8B |
| 8–10 GB | 12–14B |
| 10–14 GB | 14B |
| 14–16 GB | 14–20B |
| > 16 GB | 30B+ |
向使用者說明推薦理由，列出推薦模型清單（附 Ollama model tag）。
Step 2：確認要測試的模型
詢問使用者確認測試清單（若使用者已在指令中指定則略過）。
What ships with it
1 file 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.
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.
- 12d ago First seen · 200 lines · 82 tokens per session scan D 2fa1a6b9e496
llm-benchmark is a skill published in the GitHub repository KerberosClaw/kc_ai_skills (79 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 2,162 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ai-portable-setup
Erstellt einen portablen KI-Arbeitsbereich auf einem USB-Stick oder beliebigen Laufwerk. RAG-Pipeline mit lokalen LLM-Modellen (Ollama), Vektordatenbank (ChromaDB) und vorkonfigurierten Prompts.
compare-race
Use when the user wants to send the same prompt to several LLMs and compare the answers - sequentially (stopwatch, clean per-lane timing) or in parallel (true race), with optional repetitions per model, judged by the starting model across quality, correctness, completeness, instruction fidelity and latency (time is…
document-chunker
Split documents into overlapping token chunks for RAG pipelines and LLM context windows. Zero dependencies.
accelerate
Run PyTorch training across GPUs with minimal changes.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
pydantic-ai
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.