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 fancyboi999/goofish-cli --skill goofish-publish-itemgit clone --depth 1 https://github.com/fancyboi999/goofish-cliWrote 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/fancyboi999/goofish-cli/goofish-publish-item)<a href="https://agentmods.dev/skills/fancyboi999/goofish-cli/goofish-publish-item"><img src="https://agentmods.dev/badge/skills/fancyboi999/goofish-cli/goofish-publish-item/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/fancyboi999/goofish-cli/goofish-publish-item"><img src="https://agentmods.dev/badge/skills/fancyboi999/goofish-cli/goofish-publish-item.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 | $0.00151 | $0.01769 |
| Opus 5 | $0.00076 | $0.00885 |
| Sonnet 5 | $0.00030 | $0.00354 |
| Haiku 4.5 | $0.00015 | $0.00177 |
Grade A, and why
goofish-publish-item 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 11d 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.
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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
闲鱼发商品
工具命名
正文使用 auth_status 这类逻辑名。OpenClaw 调 goofish__<逻辑名>；
Claude Code / Cursor 调 mcp__goofish__<逻辑名>。frontmatter 的 allowed-tools
保留 Claude 权限预批准格式，OpenClaw 不读取该字段。
触发姿势
用户典型输入：
- "帮我把这个耳机发到闲鱼，300，9 成新"
- "我拍了几张图，给我写个标题和描述"
- "上架这个手办，可以议价，底线 200"
当你从用户消息中能提取 （商品本体 + 至少一张图 或 对物品的文字描述） 就启动本流程。信息不足时问用户而不是瞎猜。
标准流程（7 步）
Step 1 · 登录态自检（必做）
调 auth_status
valid=true → 继续
valid=false → 不继续；告诉用户: "登录态失效了，请执行 goofish auth login（扫码走 --qr）"，停。
Step 2 · 信息收集
从对话和用户提供的素材里提取：
| 字段 | 必填 | 来源 |
|---|---|---|
| 核心物品（是什么） | ✅ | 用户描述 / 图片识别 |
| 品牌 + 型号 | ✅ | 用户描述 |
| 成色（X 成新） | ✅ | 用户描述；没说就问 |
| 价格 | ✅ | 用户描述；没说就问 |
| 图片（URL 或本地路径） | ✅ | 用户提供 |
| 瑕疵说明 | 推荐 | 问用户"有没有瑕疵要提一下的" |
| 购买渠道 | 推荐 | 帮写描述更有信服力 |
| 是否可议价 / 底线 | 可选 | 为后续 reply-buyer 做准备 |
| 发货地 | ⚪️ | 不填就调 location_default 兜底 |
缺必填字段就停下来问，不要补默认值。
Step 3 · 类目识别
调 category_recommend(title=候选标题, images=[首图])
→ 拿到 catId / catName
结果校验：
- 如果 catName 和用户描述明显不符（比如用户说手机壳，返回"手机"），告诉用户并让他确认
- 如果置信度低（返回多个候选），展示前 3 个让用户选
Step 4 · 标题生成
按 "品牌 + 核心词 + 属性 + 场景 + 情感" 5 段式生成 3 个候选。详见 references/title-formula.md。
然后调用 goofish-risk-guard 扫描：
- 绝对化词、外联词、侵权词命中 → 重新生成
- 命中"降价改标"嫌疑（标题含促销词+历史价格变动）→ 重新生成
把扫描过的候选展示给用户选 / 改。
Step 5 · 描述生成
结构参考 references/title-formula.md 的"描述骨架"段。重点：
- 有瑕疵就大方说（保护卖家对抗仅退款）
- 说清为什么卖（"升级新款"、"不常用"，比"闲置"可信）
- 说清发货地 + 快递 + 是否包邮
- 议价政策写明（"小刀友好 / 超过 XX 勿扰"）
Step 6 · 图片处理
for image in images:
调 media_upload(image)
收集返回的 {url, width, height}
检查:
总图数 ≤ 9 ？
首图是 1:1 ？（如果不是，提示用户换首图）
张数 ≥ 3 ？（少于 3 张警告但不拦）
Step 7 · 用户最终确认 + 发布
展示给用户（强制）：
【标题】...（最终版）
【类目】catName (catId=XXXX)
【描述】
（全文）
【价格】XXX 元
【图片】9 张，首图 1:1 ✅
【发货地】XX 市 / 默认
【风控扫描】通过 ✅
是否确认发布？
等待用户明确回复 "发 / 发吧 / 确认 / OK / 是 / 嗯"。含糊的 "看看" / "嗯" 单字不算确认。
确认后：
调 item_publish(
title=...,
desc=...,
price=...,
image_urls=[...],
cat_id=...,
addr=...（没有就省略，让服务端用 location_default）
)
What ships with it
4 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.
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.
- 11d ago First seen · 166 lines · 151 tokens per session scan A d643e8cafa99
goofish-publish-item is a skill published in the GitHub repository fancyboi999/goofish-cli (191 stars, last pushed 4d ago), licensed Apache-2.0. It adds 151 tokens to every session and 1,769 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
stripe
Generated by Gutenberg. Use this skill to call the stripe API through the local stripe CLI.
amazon-automation
Automate Amazon tasks via Rube MCP (Composio). Always search tools first for current schemas.
clishop
Search products, compare stores, place orders, and manage shopping flows through CLISHOP from OpenClaw.
amazon-automation
Automate Amazon tasks via Rube MCP (Composio). Always search tools first for current schemas.
baselinker-automation
Automate Baselinker tasks via Rube MCP (Composio). Always search tools first for current schemas.
bestbuy-automation
Automate Bestbuy tasks via Rube MCP (Composio). Always search tools first for current schemas.