Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/chaterm/terminal-skillsnpx agentmods add skills/chaterm/terminal-skills/installationWrote 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/chaterm/terminal-skills/installation)<a href="https://agentmods.dev/skills/chaterm/terminal-skills/installation"><img src="https://agentmods.dev/badge/skills/chaterm/terminal-skills/installation/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/chaterm/terminal-skills/installation"><img src="https://agentmods.dev/badge/skills/chaterm/terminal-skills/installation.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 | $0.00009 | $0.02769 |
| Opus 5 | $0.00005 | $0.01385 |
| Sonnet 5 | $0.00002 | $0.00554 |
| Haiku 4.5 | $0.00001 | $0.00277 |
Grade C, and why
installation scanned grade C with 2 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.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf /opt/openclaw Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/openclaw/openclaw/main/docker-compose.yml -o docker-compose.yml How it starts
The opening of the file, as written. The whole thing — 441 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw 安装与部署
概述
OpenClaw 是一个开源的分布式任务调度和工作流编排平台,本文档涵盖各种环境下的安装部署方法。
环境要求
系统要求
# 检查系统版本
cat /etc/os-release
uname -a
# 最低要求
# - CPU: 2 核心
# - 内存: 4GB
# - 磁盘: 20GB
# - 操作系统: Linux (CentOS 7+, Ubuntu 18.04+, Debian 10+)
# 检查资源
free -h
df -h
nproc
依赖检查
# 检查 Docker
docker --version
docker info
# 检查 Docker Compose
docker-compose --version
# 检查 Java (如需原生安装)
java -version
# 检查 Python
python3 --version
pip3 --version
Docker 方式安装(推荐)
单机部署
# 创建工作目录
mkdir -p /opt/openclaw && cd /opt/openclaw
# 下载 docker-compose.yml
curl -fsSL https://raw.githubusercontent.com/openclaw/openclaw/main/docker-compose.yml -o docker-compose.yml
# 创建必要目录
mkdir -p {data,logs,config}
# 启动服务
docker-compose up -d
# 查看状态
docker-compose ps
docker-compose logs -f
自定义配置
# docker-compose.yml
version: '3.8'
services:
openclaw-server:
image: openclaw/openclaw-server:latest
container_name: openclaw-server
ports:
- "8080:8080"
- "9090:9090"
environment:
- OPENCLAW_DB_HOST=openclaw-db
- OPENCLAW_DB_PORT=3306
- OPENCLAW_DB_NAME=openclaw
- OPENCLAW_DB_USER=openclaw
- OPENCLAW_DB_PASSWORD=${DB_PASSWORD:-openclaw123}
- OPENCLAW_REDIS_HOST=openclaw-redis
- OPENCLAW_REDIS_PORT=6379
- JAVA_OPTS=-Xms1g -Xmx2g
volumes:
- ./data:/opt/openclaw/data
- ./logs:/opt/openclaw/logs
- ./config:/opt/openclaw/config
depends_on:
- openclaw-db
- openclaw-redis
restart: unless-stopped
openclaw-worker:
image: openclaw/openclaw-worker:latest
container_name: openclaw-worker
environment:
- OPENCLAW_SERVER_HOST=openclaw-server
- OPENCLAW_SERVER_PORT=9090
- WORKER_GROUP=default
- WORKER_THREADS=8
volumes:
- ./logs:/opt/openclaw/logs
depends_on:
- openclaw-server
restart: unless-stopped
deploy:
replicas: 2
openclaw-db:
image: mysql:8.0
container_name: openclaw-db
environment:
- MYSQL_ROOT_PASSWORD=${DB_ROOT_PASSWORD:-root123}
- MYSQL_DATABASE=openclaw
- MYSQL_USER=openclaw
- MYSQL_PASSWORD=${DB_PASSWORD:-openclaw123}
volumes:
- ./data/mysql:/var/lib/mysql
restart: unless-stopped
openclaw-redis:
image: redis:7-alpine
container_name: openclaw-redis
command: redis-server --appendonly yes
volumes:
- ./data/redis:/data
restart: unless-stopped
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.
- 9d ago First seen · 441 lines · 9 tokens per session scan C f5847155f02e
installation is a skill published in the GitHub repository chaterm/terminal-skills (58 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 9 tokens to every session and 2,769 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, 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
skillci-guardrails
Use this skill whenever you create, edit, or review a Claude Skill — any SKILL.md file, or the eval cases/config next to one. Most SKILL.md files today are written or edited by an agent, not typed by hand, so this closes the loop by having the agent that just wrote the skill also author it defensively and verify it…
mle-workflow
Production ML engineering workflow — data contracts, reproducible training, evaluation gates, deployment, and monitoring. Use when building, reviewing, or hardening ML systems beyond notebooks.
cicd-agent
CI/CD pipeline design and review — GitHub Actions, pipeline best practices, secrets management, deployment strategies, and release automation.
example-skill
Writes a single changelog entry summarizing a code change, given a short description of what changed.
clean-skill
A skill with no lint issues, used as a starting point for the lint-on-type test.
skill-with-referenced-issue
Has a clean SKILL.md but an unsafe referenced script.