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 agentmods add skills/geniusdapeng-collab/super-mickey/data-mining-enginenpx skills add geniusdapeng-collab/super-mickey --skill data-mining-enginegit clone --depth 1 https://github.com/geniusdapeng-collab/super-mickeyWrote 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/geniusdapeng-collab/super-mickey/data-mining-engine)<a href="https://agentmods.dev/skills/geniusdapeng-collab/super-mickey/data-mining-engine"><img src="https://agentmods.dev/badge/skills/geniusdapeng-collab/super-mickey/data-mining-engine.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00137 | $0.03220 |
| Opus 5 | $0.00068 | $0.01610 |
| Sonnet 5 | $0.00027 | $0.00644 |
| Haiku 4.5 | $0.00014 | $0.00322 |
Grade A, and why
data-mining-engine 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 3d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
珍妮纺织机 · 数据挖掘引擎 — 执行手册
隐喻：把棉花（散落的商品信息）纺成纱布（结构化情报档案）， 供下游裁剪成各种衣服（Brief / 主题 / PRD / 镜头提示词）。
一、模块定位与铁律
定位：全链路最上游（Stage -2），营销/商品模式强制激活，纯故事模式跳过。 与主链路松耦合：档案命中即复用，未命中才跑流水线，任何故障不得阻塞主流程。
五条铁律（全 Agent 通用，违者出站即被闸机拦截）：
- 无源不入库：每条事实/观点必须挂证据编号（EvidenceLedger 登记）， 无来源的内容一律剔除并记入 gaps。
- 置信度三级：confirmed（官方或 ≥2 独立来源）/ reported（单一来源）/ inferred（推理）。inferred 禁止进入 pros/cons 事实区与任何摘要卡。
- 原文不改写：用户评价的语义一字不改，聚合只做归类不做润色。
- 缺站显式标记：采集不到的维度写进 gaps，禁止留空装作完整。
- 禁止虚构外观：商品图必须真实来源，AI 生成图/概念图/渲染图直接出局。
二、运行模式
| 模式 | 流程 | 适用 |
|---|---|---|
| spec | engine.plan(input) 产出三份《任务书》→ 执行 Agent 就地检索回填 → engine.assemble(traceId, input, raw) |
LLM 就地执行（supermickey-studio 技能运行时默认） |
| api | engine.run(input) 全自动 |
注入 executor(stage, plan) 检索执行器的环境 |
输入契约：{ name(必填), brand?, category?, model?, price_band?, sellingPointCandidates? }
三、流水线协议（Agent 间数据管道）
input
→ [A1] --信封--> [A2] --信封--> [A3] --信封--> [A4] --信封--> [A5]
每站出站必过两道关：Envelope.verify（完整性）→ HandoffValidator（契约闸机）
证据账本（EvidenceLedger）全程共享，证据编号随信封流转
- 信封：
{ envelope_id, trace_id, stage, agent, mode, payload, evidence_refs, prev_checksum, checksum, created_at }。 校验和 sha256 链式锁定，防串包防跳站；trace_id 全程一致，任何情报可倒查。 - 闸机三层：L1 结构硬校验（缺必填→阻断）；L2 纪律硬校验（事实区无证据编号→阻断）； L3 丰度软校验（量不足→放行但记 gap）。
- 缺站降级：A1 是硬依赖（身份事实缺失全线停摆）；A2/A3 缺站记 gap 继续， 档案照样装订，下游只看到"标记了缺口"的档案。
四、Agent 分册
A1 商品情报采集员（ProductInfoCollector）
使命：把"官方事实"和"真实外观"钉死。
任务书（plan）产出：
- 查询矩阵（实物 8 路 / 服务 6 路）：官网、旗舰店商品页、参数规格、价格、 官方产品图、实拍开箱、白底图；带型号时追加"型号甄别"查询（剔除同系列旧款）。
- 提取模板：身份字段 + 规格字段提示 + 价格规则（全价格样本，禁单一价格，币种必标）。
- 回填格式：identity（每个规格值可带 source_url）+ images（url/source/page_url/angle/尺寸）。
蒸馏（distill）逻辑：
- 规格表只收带来源的键值，无源规格保留但记 gap 降级。
- 价格带归一：全样本取 min-max 区间。
- 官方卖点无源剔除（出事实区，记 gap）。
- 商品图逐张评分：官方渠道 +30 / 电商详情 +15 / 短边≥800px +20 / 带角度 +5 /
AI 嫌疑 -100（出局）/ 水印 -10。按分排序，第一名即英雄照候选，
编号
{品牌前缀}-HERO-001，其余-REF-NNN。 - 授权风险分级：官方 low / 电商 mid / 其他 high（只标记不拦截，图仅作定妆照参考）。
- 有效图低于 2 张打
needs_more_reference（与定妆照门槛对齐）。
What ships with it
13 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.
- agents/competitor-scout.js 8.3 KB runs code
- agents/cross-verifier.js 7.0 KB runs code
- agents/dossier-binder.js 5.7 KB runs code
- agents/product-info-collector.js 12 KB runs code
- agents/review-miner.js 14 KB runs code
- contracts/confirmation-sheet.js 3.5 KB runs code
- contracts/dossier-schema.js 5.9 KB runs code
- contracts/summary-cards.js 7.7 KB runs code
- index.js 9.9 KB runs code
- pipeline/dossier-store.js 4.2 KB runs code
- pipeline/evidence-ledger.js 4.1 KB runs code
- pipeline/handoff-validator.js 5.2 KB runs code
- pipeline/message-envelope.js 3.0 KB runs code
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 · 188 lines · 137 tokens per session scan A 6d184cbdd730
data-mining-engine is a skill published in the GitHub repository geniusdapeng-collab/super-mickey (5 stars, last pushed 8d ago), licensed MIT. It adds 137 tokens to every session and 3,220 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
contextual-commit
Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.
repomix-explorer
Analyze or explore a codebase (remote or local repository) by packing it with the Repomix CLI, then reading and searching the generated output. Use when the user wants a high-level understanding of an unfamiliar or large repo, not a targeted edit. Trigger for: Structure/overview: "analyze this repo", "what's the…
repomix
Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
browser-extension-developer
Use this skill when developing or maintaining browser extension code in the browser/ directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.
website-maintainer
Use this skill when working on the Repomix documentation website in website/ directory, including VitePress configuration, multi-language content, or translation workflows.