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 qgis-processgit 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/qgis-process)<a href="https://agentmods.dev/skills/znlgis/opengis-skills/qgis-process"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/qgis-process/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/qgis-process"><img src="https://agentmods.dev/badge/skills/znlgis/opengis-skills/qgis-process.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00048 | $0.03263 |
| Opus 5 | $0.00024 | $0.01631 |
| Sonnet 5 | $0.00010 | $0.00653 |
| Haiku 4.5 | $0.00005 | $0.00326 |
Grade A, and why
qgis-process 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 371 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目地址: https://github.com/qgis/QGIS
文档地址: https://github.com/qgis/QGIS-Documentation
在线文档: https://docs.qgis.org/4.2/en/docs/user_manual/processing/standalone.html
许可证: GPL-2.0+
概述
qgis_process 是 QGIS 自带的命令行工具(QGIS Processing Executor),允许在不启动 QGIS 桌面应用的情况下,直接从命令行运行 Processing 算法和模型(内置算法或由插件提供)。它适用于服务器端批量处理、CI/CD 自动化流水线、脚本化 GIS 工作流等场景。
源码位置:src/process/ 目录下的 main.cpp、qgsprocess.cpp、qgsprocess.h。
环境准备
前置条件
- 安装 QGIS 3.16+(
qgis_process从 QGIS 3.16 开始可用) - 确保
qgis_process可执行文件在PATH中
无窗口系统(Headless 服务器)
在没有窗口管理器的系统上运行前,需设置环境变量:
export QT_QPA_PLATFORM=offscreen
验证安装
qgis_process --version
命令行语法
qgis_process [--help] [--version] [--json] [--verbose] [--no-python] [--skip-loading-plugins] [command] [algorithm id | model path | script path] [parameters]
全局选项
| 选项 | 说明 |
|---|---|
--help 或 -h |
输出帮助信息 |
--version 或 -v |
输出 QGIS Process 相关的所有版本信息 |
--json |
以 JSON 格式输出结果(AI/脚本友好) |
--verbose |
输出详细日志 |
--no-python |
禁用 Python 支持(启动更快) |
--skip-loading-plugins |
跳过加载已启用的插件(启动更快) |
可用命令
| 命令 | 说明 |
|---|---|
plugins |
列出可用和已激活的插件 |
plugins enable <name> |
启用已安装的插件 |
plugins disable <name> |
禁用已安装的插件 |
list |
列出所有可用的 Processing 算法 |
help <algorithm_id> |
显示指定算法的帮助信息 |
run <algorithm_id> [-- PARAM=VALUE ...] |
运行指定算法 |
注意: 只有在
metadata.txt中声明了hasProcessingProvider=yes的已安装插件才能被qgis_process识别和加载。
核心用法
1. 列出所有算法
qgis_process list
输出所有已注册 Provider 及其提供的算法 ID。
2. 查看算法帮助
qgis_process help qgis:regularpoints
输出算法的描述、参数列表(名称、类型、默认值、是否可选)和输出定义。
JSON 格式帮助(推荐 AI 使用)
qgis_process help native:buffer --json
JSON 输出结构:
{
"qgis_version": "...",
"algorithm_details": {
"id": "native:buffer",
"name": "Buffer",
"tags": ["..."]
},
"provider_details": {
"id": "native",
"name": "QGIS (native c++)"
},
"parameters": {
"INPUT": {
"name": "INPUT",
"description": "Input layer",
"type": {
"id": "source",
"name": "Vector Features",
"acceptable_values": ["Path to a vector layer"]
},
"optional": false,
"default_value": null
},
"DISTANCE": {
"name": "DISTANCE",
"description": "Distance",
"type": {
"id": "distance",
"name": "Distance"
},
"optional": false,
"default_value": 10
},
"OUTPUT": {
"name": "OUTPUT",
"description": "Buffered",
"type": {
"id": "sink",
"name": "Vector Layer Destination"
},
"is_destination": true,
"optional": false
}
},
"outputs": {
"OUTPUT": {
"description": "Buffered",
"type": "outputVector"
}
}
}
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.
- yesterday Changed 4b180e948f81
- 8d ago First seen · 371 lines · 48 tokens per session scan A 594a6f143526
qgis-process is a skill published in the GitHub repository znlgis/opengis-skills (60 stars, last pushed 2d ago), licensed MIT. It adds 48 tokens to every session and 3,263 once invoked, about $0.0002 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.
Other skills, from other repositories
atmos-ci
Atmos CI: Native CI with GitHub Actions containers, native outputs, SBOM workflow-artifact publication, collapsible log groups, affected/all matrix workflows, OIDC profiles, toolchain-aware jobs, drift routing to Atmos Pro, deployment approvals, merge queues, environments, statuses, and Atlantis integration.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
atmos-modernization
Atmos Modernization: migrate deprecated or legacy Atmos patterns to current names, Native CI, Atmos Pro drift detection, dependencies.components, nametemplate, and declared secrets.
atmos-lint
Atmos Terraform linting with TFLint: standalone atmos terraform lint, component-aware config discovery and toolchain versions, TFLint rule configuration, and lifecycle hooks/CI findings. Use when configuring, running, debugging, or documenting Terraform/OpenTofu linting in an Atmos project.
atmos-pro
Atmos Pro setup and workflows: settings.pro, GitHub OIDC, affected and inventory uploads, stack locks, pro commit, workflow dispatch, merge queues, and drift detection.
atmos-sbom
Atmos SBOM provenance: CycloneDX and SPDX generation from vendor and Terraform evidence, coverage diagnostics, NTIA validation, and native CI workflow-artifact publication.