An agent that delegates image, video, and other creative-production tasks to the Gouda service. It also supports continuing, recovering, cancelling, and checking those tasks.

Use it to request or manage image and video production tasks, including recovery and delivery-related workflows.

It provides one supported route for managing remote creative jobs instead of requiring direct access to the service’s internal tools.

gouda-agent — Skill for Claude Code by HiDream-ai

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 HiDream-ai/vivago-agent-cli --skill gouda-agent

Clone the repo

git clone --depth 1 https://github.com/HiDream-ai/vivago-agent-cli

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hidream-ai/vivago-agent-cli/gouda-agent/github.svg)](https://agentmods.dev/skills/hidream-ai/vivago-agent-cli/gouda-agent)

Your own site

<a href="https://agentmods.dev/skills/hidream-ai/vivago-agent-cli/gouda-agent"><img src="https://agentmods.dev/badge/skills/hidream-ai/vivago-agent-cli/gouda-agent/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hidream-ai/vivago-agent-cli/gouda-agent"><img src="https://agentmods.dev/badge/skills/hidream-ai/vivago-agent-cli/gouda-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,407 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00056	$0.02407
Opus 5	$0.00028	$0.01203
Sonnet 5	$0.00011	$0.00481
Haiku 4.5	$0.00006	$0.00241

Measured 3d ago against content hash a5733a8ff6b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-13, from the pricing page.

Security

Grade A, and why

gouda-agent scanned grade A with 1 finding 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 3d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/artifact.js, scripts/auth.js, scripts/client.js, …), 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

沙箱或无法打开用户本机浏览器的环境，不要降级成 curl 或要求用户复制凭证；说明必须在本地

integrations/workbuddy/gouda-agent/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

够搭 Agent 任务委派

使用本 Skill 自带的 node scripts/gouda-agent.js ... 作为唯一集成边界。不要搜索、安装或调用 Go CLI、六平台二进制和 npm 依赖，不要自行拼接 HTTP 请求，也不要调用、枚举或猜测够搭 Agent 内部的 MCP 工具和 Skill。

脚本固定连接国内正式环境。以脚本配置的 API、登录地址和返回链接为准，不增加环境切换参数，不改写 origin，也不调用未配置的接口。回复用户时使用用户当前使用的语言；命令、标识符和文件路径保持原样。

详细流程放在本文件旁边的 references/，到对应阶段再读取：

@references/brief-guide.md — 编写图片和视频 brief 前读取
@references/recovery-runbook.md — 视频后台执行、流中断、任务恢复或重新进入时读取
@references/output-shapes.md — 解析命令 JSON/JSONL 输出和查找最终产物时读取
@references/delivery-playbook.md — 收到终态后校验、预览和交付产物时读取
@references/capability-limits.md — 用户要求字幕、音效、指定 TTS 声音或其他边界能力时读取
@references/commands.md — 需要确认命令、参数和退出码时读取
@references/authentication.md — 需要登录、刷新、退出或排查认证问题时读取
@references/api-contract.md — 排查协议或国内外接口差异时读取
@references/security-and-privacy.md — 涉及凭证、本地文件、数据范围或安全说明时读取

运行环境检查

本 Skill 需要 Node.js 18 或更高版本。首次使用先运行：

node scripts/gouda-agent.js doctor

登录依赖当前设备上的默认浏览器和本机 127.0.0.1 回调。如果 WorkBuddy 运行在容器、远程沙箱或无法打开用户本机浏览器的环境，不要降级成 curl 或要求用户复制凭证；说明必须在本地桌面版 WorkBuddy 中完成登录。

前置检查

运行 node scripts/gouda-agent.js auth status。
如果未登录，先告诉用户即将打开够搭登录页，再运行 node scripts/gouda-agent.js auth login。若 stderr 返回手动登录 URL，只把它交给当前用户打开；不要代填账号，不要要求用户复制 ticket 或 refresh token。
登录成功后立即告知用户并继续原任务，不要停在登录结果。
运行 node scripts/gouda-agent.js state list。如果存在未完成 Turn，先说明发现的状态并优先恢复，不要重复提交原 prompt。

WorkBuddy 的登录和任务状态保存在独立命名空间，不读取或修改现有 Go CLI 的凭证与状态。

提交前

在线图片搜索是每个新 Turn 的显式能力。只有用户要求查找在线图片、视觉参考，或明确授权在线视觉素材发现时才增加 --image-search。生成图片或视频本身不构成搜索授权。
一次性确认真正影响结果的硬约束：视频总时长、比例或目标平台、参考图片或素材、配音和字幕需求。不要替用户发明硬约束；用户不指定时，说明采用的默认值。
视频会消耗真实额度，常见耗时约 15–40 分钟。提交前用一条消息概括总时长、比例、场景数和关键内容；发生 RUN_ERROR 后再次提交也要重新概括并取得用户确认。
按 @references/brief-guide.md 编写 brief。视频分镜使用编号场景，不写逐场景时间戳；总时长只在整体要求中写一次；有参考图时写清外观锁定；配音逐句写出。
图片任务走轻量流程，不询问视频时长、分镜、配音等无关参数。

创建并提交任务

用户没有提供 Project ID 时，创建一个名称简短且不含敏感信息的 v3 Project：

node scripts/gouda-agent.js project create --name "<简短名称>"

提交新任务：

node scripts/gouda-agent.js ask --project-id "<project-id>" --prompt "<完整任务>"

Read the full file on GitHub · 178 lines

Files

What ships with it

19 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.

3d ago First seen · 178 lines · 56 tokens per session scan A a5733a8ff6b4

Subscribe to this mod's changes

gouda-agent is a skill published in the GitHub repository HiDream-ai/vivago-agent-cli (8 stars, last pushed 4d ago), licensed Apache-2.0. It adds 56 tokens to every session and 2,407 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-10.

Creative and media 公众号

gouda-agent

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Makes network callslowCapability

How it starts

够搭 Agent 任务委派

运行环境检查

前置检查

提交前

创建并提交任务

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

article-magazine

card-xiaohongshu

data-report

card-twitter

poster-hero

deck-ljg-present