abuse-hunter

abuse-hunter is a skill for Claude Code, Codex from nexu-io/harness-engineering-guide. It costs 86 tokens per session (3,041 once invoked), scanned A, original, MIT.

A SaaS abuse-investigation skill for finding bulk account registration and free-credit misuse. SaaS means software delivered as an online service.

In plain words
What is it for?
Use it with a user database or CSV/JSON export to analyze email domains, registration timing, browser fingerprints, sessions, usage, and credit consumption, then produce an abuse score.
Why use it?
It helps explain sudden user growth, falling paid conversion, or unusually fast credit consumption by examining several kinds of account and usage data.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it with a user database or CSV/JSON export to analyze email domains, registration timing, browser fingerprints, sessions, usage, and credit consumption, then produce an abuse score.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nexu-io/harness-engineering-guide/abuse-hunter
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 nexu-io/harness-engineering-guide --skill abuse-hunter
Clone the repo
git clone --depth 1 https://github.com/nexu-io/harness-engineering-guide

Made for: Claude Code, Codex.

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.

agentmods badge for abuse-hunter

README.md
[![agentmods](https://agentmods.dev/badge/skills/nexu-io/harness-engineering-guide/abuse-hunter/github.svg)](https://agentmods.dev/skills/nexu-io/harness-engineering-guide/abuse-hunter)
Your own site
<a href="https://agentmods.dev/skills/nexu-io/harness-engineering-guide/abuse-hunter"><img src="https://agentmods.dev/badge/skills/nexu-io/harness-engineering-guide/abuse-hunter/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.

agentmods 80×15 button for abuse-hunter

Your own site · 80×15
<a href="https://agentmods.dev/skills/nexu-io/harness-engineering-guide/abuse-hunter"><img src="https://agentmods.dev/badge/skills/nexu-io/harness-engineering-guide/abuse-hunter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,041 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 53
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00086 $0.03041
Opus 5 $0.00043 $0.01520
Sonnet 5 $0.00017 $0.00608
Haiku 4.5 $0.00009 $0.00304

Measured 9d ago against content hash 5030bdb98c98, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

abuse-hunter 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/analyze.py), 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.

curl -s "https://api.vvhan.com/api/icp?url=<domain>" | jq .
skills/abuse-hunter/SKILL.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Abuse Hunter — SaaS 批量注册盗刷排查 Skill

一键排查你的 SaaS 平台是否存在批量注册、薅免费额度、账号农场等滥用行为。

何时使用

  • 发现某个邮箱域名注册量异常高
  • 新用户暴增但付费转化率下降
  • 免费积分/credit 消耗速度突然加快
  • 怀疑存在自动化注册行为

排查流程(6 步)

按顺序执行,每一步都会输出中间结论,最终汇总为综合评分。

Step 1: 邮箱域名聚类

目标:找出注册量异常高的邮箱域名

-- 按邮箱域名统计注册用户数,找出 Top 异常域名
SELECT
  SUBSTRING(email FROM '@(.+)$') AS domain,
  COUNT(*) AS user_count,
  MIN(created_at) AS first_signup,
  MAX(created_at) AS last_signup,
  EXTRACT(EPOCH FROM MAX(created_at) - MIN(created_at)) / 3600 AS span_hours
FROM users
GROUP BY domain
HAVING COUNT(*) > 10
ORDER BY user_count DESC
LIMIT 20;

判定标准

  • 🔴 单域名 >100 注册 + 域名年龄 <30 天 → 高风险
  • 🟡 单域名 50-100 注册 + 注册集中在 <72h 内 → 中风险
  • 🟢 单域名 <50 注册 + 分布均匀 → 低风险

域名背景检查

# WHOIS 查域名创建时间和注册商
whois <domain> | grep -iE "creation|registrar|name server"
# DNS 检查:有没有网站,有没有邮件配置
dig <domain> MX +short
dig <domain> A +short
# 是否有 ICP 备案(仅中国域名)
curl -s "https://api.vvhan.com/api/icp?url=<domain>" | jq .

Step 2: 注册时间模式分析

目标:判断注册节奏是自然增长还是批量注入

-- 按天统计注册量(可疑域名)
SELECT
  DATE(created_at) AS reg_date,
  COUNT(*) AS daily_count
FROM users
WHERE email LIKE '%@<suspect_domain>'
GROUP BY reg_date
ORDER BY reg_date;

-- 按小时统计(找注册高峰)
SELECT
  DATE(created_at) AS reg_date,
  EXTRACT(HOUR FROM created_at) AS reg_hour,
  COUNT(*) AS hourly_count
FROM users
WHERE email LIKE '%@<suspect_domain>'
GROUP BY reg_date, reg_hour
HAVING COUNT(*) > 10
ORDER BY hourly_count DESC;

-- 注册间隔分析(关键!)
WITH ordered AS (
  SELECT created_at,
    LAG(created_at) OVER (ORDER BY created_at) AS prev_at
  FROM users
  WHERE email LIKE '%@<suspect_domain>'
)
SELECT
  PERCENTILE_CONT(0.5) WITHIN GROUP (ORDER BY EXTRACT(EPOCH FROM created_at - prev_at)) AS median_interval_sec,
  PERCENTILE_CONT(0.9) WITHIN GROUP (ORDER BY EXTRACT(EPOCH FROM created_at - prev_at)) AS p90_interval_sec
FROM ordered
WHERE prev_at IS NOT NULL;

判定标准

  • 🔴 注册间隔中位数 <60 秒 → 自动化注册
  • 🟡 注册间隔中位数 60-300 秒 + 存在明显高峰 → 疑似批量
  • 🟢 注册间隔中位数 >300 秒 + 无明显聚集 → 自然注册

阶段切换检测: 将注册按时间分段,检查是否存在"前期小量试探 + 后期大量涌入"模式。如果存在,说明攻击者经历了"测试→放量"的阶段。

Read the full file on GitHub · 329 lines

Files

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.

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.

  1. 9d ago First seen · 329 lines · 86 tokens per session scan A 5030bdb98c98

Subscribe to this mod's changes

abuse-hunter is a skill published in the GitHub repository nexu-io/harness-engineering-guide (638 stars, last pushed 4mo ago), licensed MIT. It adds 86 tokens to every session and 3,041 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens