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-risk-guardgit 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-risk-guard)<a href="https://agentmods.dev/skills/fancyboi999/goofish-cli/goofish-risk-guard"><img src="https://agentmods.dev/badge/skills/fancyboi999/goofish-cli/goofish-risk-guard/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-risk-guard"><img src="https://agentmods.dev/badge/skills/fancyboi999/goofish-cli/goofish-risk-guard.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 | $0.00194 | $0.01532 |
| Opus 5 | $0.00097 | $0.00766 |
| Sonnet 5 | $0.00039 | $0.00306 |
| Haiku 4.5 | $0.00019 | $0.00153 |
Grade A, and why
goofish-risk-guard 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 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.
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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
闲鱼风控预检
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。
定位
这是 被其它 skill 频繁调用的知识库型 skill。Agent 读它的 references，不一定要调 MCP 工具。
其它 skill 什么时候应该引用本 skill：
| 上游 skill | 引用点 |
|---|---|
goofish-publish-item |
标题/描述生成后、发布前 → forbidden-words.md + publish-red-lines.md |
goofish-reply-buyer |
起草回复后、send 前 → external-contact-keywords.md |
goofish-shop-diagnosis |
归因分析阶段 → publish-red-lines.md 里的降权触发项 |
三道闸门
闸门 1 · 发布前扫描
输入：标题 / 描述 / 价格 / 图片数 / 类目 / 历史价格（若有）
输出：{ blockers: [...], warnings: [...], suggestions: [...] }
blockers（必须改，否则拒绝发布）：
- 绝对化词（最/顶/第一/绝对/全网最低等，详见
forbidden-words.md） - 外联词（同上，消息和商品描述都禁）
- 品牌侵权（非授权卖 Nike/LV 等一线品牌）
- 类目明显错放（比如"手机壳"放到"数码-手机"）
warnings（建议改）：
- 标题缺结构（没品牌 / 没核心词 / 没规格）
- 图片 < 3 张
- 首图非 1:1
- 描述 < 30 字（信息不足，买家不问直接跳过）
suggestions（可选优化）：
- 按"品牌+核心词+属性+场景+情感" 5 段式补全
- 建议加成色描述（95 新 / 8 成新 / 有瑕疵具体说明）
具体规则见 references/publish-red-lines.md。
闸门 2 · 发消息前扫描
输入：草稿 text
输出：{ block: bool, reason: str, replacement: str | None }
命中规则（详见 references/external-contact-keywords.md）：
- 外联关键词 →
block=True，提供合规替换 - 诱导线下担保 →
block=True - 误导性承诺（"包真"、"假一赔十"但无凭证）→
warning - 情绪失控词（"你脑子有病"、"去死"）→
warning
闸门 3 · RGV587 / x5sec 恢复
当 MCP 调用返回 FAIL_SYS_ILLEGAL_ACCESS 或 RGV587：
不要做：
- 重试（会进一步触发风控）
- 建议用户
auth_login（覆盖 cookie 后丢失 x5sec，更糟） - 建议用户
auth reset-guard（只解本地熔断，不解服务端）
要做（按顺序）：
- 告诉用户：服务端风控已触发，原因可能是短时高频写 / 多号同 IP / 新增风险行为
- 引导用户：打开浏览器登录闲鱼，正常浏览 3-5 分钟，触发
x5sec/mtop_partitioned_detectcookie 下发 - 用户执行
goofish auth login --browser chrome重新导入（带 x5sec） - 如果仍失败 → 建议 2-6 小时后再来
详见 references/x5sec-recovery.md。
决策框架：什么时候"拒绝帮忙"
这些请求 拒绝并解释，不要找绕过路径：
| 用户请求 | 为什么拒 |
|---|---|
| "帮我写个微信号的隐藏方式" / "帮我躲过外联词检测" | 违反平台规则 + 本工具合规声明红线 |
| "帮我刷单/做假交易" | 同上 |
| "帮我批量注册小号" / "帮我伪造设备 ID" | 同上 |
| "帮我把这个假货说成真的" | 欺诈 |
| "帮我写差评报复别的卖家" | 恶意 |
| "帮我规避封号后的账号找回" | 绕过平台风控 |
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.
- 10d ago First seen · 119 lines · 194 tokens per session scan A 0a93e89cdb81
goofish-risk-guard is a skill published in the GitHub repository fancyboi999/goofish-cli (191 stars, last pushed 3d ago), licensed Apache-2.0. It adds 194 tokens to every session and 1,532 once invoked, about $0.0010 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
atmos-aws-compliance
AWS compliance commands in Atmos: atmos aws compliance report, Security Hub standards, CIS AWS, PCI DSS, SOC2, HIPAA, NIST, report formats, AI summaries.
magpie-license-compliance-audit
Read-only license compliance audit for one repository or a local checkout. Checks that a LICENSE file exists, that a NOTICE file is present and complete when required by the declared license, and that source files carry SPDX-License-Identifier headers consistent with the project's declared license. Produces a grouped…
stripe
Generated by Gutenberg. Use this skill to call the stripe API through the local stripe CLI.
auto-deletion-workflow
Implements automated data deletion workflows for GDPR Article 17 right to erasure and retention period expiry. Covers cascading deletion across dependent systems, dependency handling for referential integrity, confirmation logging, and audit trail generation. Activate for automated deletion, erasure automation, data…
anonymization-alternative
Evaluates anonymization as a retention alternative under GDPR Recital 26, applying the WP29 Opinion 05/2014 techniques including randomization and generalization. Validates anonymization effectiveness using k-anonymity, l-diversity, and t-closeness metrics. Activate for anonymization, de-identification, k-anonymity…
morocco-ecommerce-compliance-audit-omar-laftouh
Performs a legal compliance audit for a Moroccan e-commerce website, focused on personal data protection (Law 09-08) and consumer contract disclosures/obligations (Law 31-08). Use this skill when a user asks to audit, check, or assess the legal compliance of an e-commerce website operating in Morocco — presence and…