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 znlgis/opengis-skills --skill opencodegit clone --depth 1 https://github.com/znlgis/opengis-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/znlgis/opengis-skills/opencode)<a href="https://agentmods.dev/skills/znlgis/opengis-skills/opencode"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/opencode/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/znlgis/opengis-skills/opencode"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/opencode.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 | $0.00052 | $0.02870 |
| Opus 5.5 | $0.00021 | $0.01148 |
| Sonnet 5.5 | $0.00010 | $0.00574 |
| Haiku 4.5 | $0.00005 | $0.00287 |
Grade D, and why
opencode 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 10d 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 pacman -S opencode # Arch 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.
curl -fsSL https://opencode.ai/install | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://opencode.ai/install | bash How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目地址： https://github.com/anomalyco/opencode
官网 / 文档： https://opencode.ai ｜ 配置 Schema： https://opencode.ai/config.json ｜ TUI Schema： https://opencode.ai/tui.json
许可证： MIT 版本： 迭代快，以本机
opencode --version为准（2026-10-11 上游最新 Release 为 v1.19.0）
注意： OpenCode 迭代非常快，命令、配置字段与模型名称请以你当前版本的
opencode --help、TUI 内/help及在线 JSON Schema 为准。
概述
OpenCode 是一个以终端为核心的开源 AI 编码智能体（区别于 IDE 内联补全），可读代码、改代码、跑命令、调用工具，自主完成多步开发任务。核心理念是「模型无关 + 配置即代码」：
- 模型无关：基于 AI SDK 与 Models.dev 支持 75+ 提供商，云端（Claude/GPT/Gemini/Qwen）与本地（Ollama/LM Studio/llama.cpp）自由切换。
- 权限系统：每类工具（edit/bash/read/webfetch 等）可设
allow/ask/deny，支持按命令、路径的细粒度规则。 - 上下文与成本可控：自动压缩（compaction）、工具输出裁剪（prune）、小模型分流（
small_model）。 - 配置即代码：
opencode.json、AGENTS.md、自定义命令/Agent/Skill 都是纯文本，可提交进 Git、团队共享。 - 三种形态：TUI（终端交互）、CLI（
opencode run脚本化/CI）、Server/SDK（opencode serve暴露 HTTP API）。 - Git 快照：
/undo、/redo依赖项目为 Git 仓库，可随时撤销 AI 改动。
安装
# 一键安装脚本（最简单）
curl -fsSL https://opencode.ai/install | bash
# 包管理器
npm install -g opencode-ai # Node 生态（npm/bun/pnpm/yarn）
brew install anomalyco/tap/opencode # macOS/Linux 官方 tap（更新最及时）
scoop install opencode # Windows
sudo pacman -S opencode # Arch
mise use -g opencode
nix run nixpkgs#opencode
opencode --version # 验证
Windows 推荐在 WSL 中使用；TUI 在 WezTerm/Alacritty/Ghostty/Kitty 等现代终端渲染更佳。
快速上手
cd your-project # 建议是 Git 仓库（/undo /redo /快照依赖 Git）
opencode # 启动 TUI
TUI 内常用斜杠命令：
/connect # 接入模型提供商（粘贴 API Key；或选 OpenCode Zen 网关）
/models # 选择当前模型
/init # 生成项目级 AGENTS.md（让 OpenCode 了解你的项目）
/undo /redo # 基于 Git 快照撤销/重做 AI 改动
/share # 生成会话分享链接
/help # 查看全部命令
也可用环境变量提供密钥（如 ANTHROPIC_API_KEY、OPENAI_API_KEY），启动时自动识别。
CLI / 无头模式（脚本与 CI）
opencode run "为 utils.ts 补充单元测试并运行" # 单次执行
opencode run -m anthropic/claude-sonnet-4-5 "重构登录模块"
opencode serve --port 4096 # 启动 HTTP Server（配合 SDK）
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.
- 10d ago Changed · +9 lines 25a38e326845
- 1mo ago First seen · 227 lines · 52 tokens per session scan D 13ba0ff2b548
opencode is a skill published in the GitHub repository znlgis/opengis-skills (72 stars, last pushed 5d ago), licensed MIT. It adds 52 tokens to every session and 2,870 once invoked, about $0.0002 per session on Opus 5.5. 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
gpt-image-gen
MUST read before generating images. Prompt-crafting guide for gpt-image-2.5 covering tool routing (native imagegeneration server tool vs the generateimage tool), model and quality selection, prompt structure, exact text rendering, reference-image editing, transparent assets, output formats, and multi-turn refinement.
tmux-manual-qa
Run a single manual tmux-based QA scenario for the todo continuation feature against the real CLI (./pi-test.sh) in an interactive TUI. Captures scrollback, asserts deterministic pass/fail count markers, and cleans up test fixtures. Use only for the manual-qa milestone features.
coding-agent-extension-worker
Implements a single feature in the pi-mono todotools builtin extension work. Use for refactoring, continuation runtime, config resolver, prompt builder, test authoring, golden snapshots, CHANGELOG entries, and harness helpers. Does NOT do manual tmux QA.
bun-1-4
Read before a js eval cell that installs a package, spawns a server or PTY, or starts a long run, and before any bun -e, script, server, CLI, test, bundle, or package-management work: this session's eval js kernel runs Bun 1.4+ (this skill is present only when it does). Bun 1.4 ships builtins that replace 15+ npm deps…
ahk-test
Design, write, and run behavior-focused tests for an objective or existing code. Writes test files only and reports evidence. No tasks created, no harness tracking.
ahk-review
Preview a code review against ticket/objective alignment, with deep semantic (name-vs-behavior) analysis. No tasks created, no harness tracking.