agentmods.dev

ClueArk: Instructions file for Codex

AGENTS.md

ClueArk AGENTS.md is an instructions file for Codex, OpenCode from lqomg/ClueArk. It costs 2,255 tokens per session, scanned A, original, MIT.

Repository guidance for ClueArk, an AI information-aggregation platform that collects and organizes public sources such as RSS feeds and web pages.

In plain words
What is it for?
Use it when working on ClueArk's React front end, NestJS APIs, crawler, MongoDB setup, monitoring, or related modules.
Why use it?
It gives contributors a shared map of the project, its services, deployment setup, and architectural rules.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is lqomg/ClueArk's own configuration. It tells Codex and OpenCode how to work on ClueArk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ClueArk configures →

not rated 53repo 3mo ago A scan 2,255 tokens original MIT
View source ↗ lqomg/ClueArk clueark.com
Reuse

Borrowing it

Nothing to install: this file belongs to lqomg/ClueArk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lqomg/ClueArk/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/lqomg/ClueArk

Made for: Codex, OpenCode.

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 ClueArk AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lqomg/clueark/agents-md/github.svg)](https://agentmods.dev/instructions/lqomg/clueark/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lqomg/clueark/agents-md"><img src="https://agentmods.dev/badge/instructions/lqomg/clueark/agents-md/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 ClueArk AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lqomg/clueark/agents-md"><img src="https://agentmods.dev/badge/instructions/lqomg/clueark/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,255 This file is loaded in full into every session.
When invoked 2,255 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02255 $0.02255
Opus 5.5 $0.00902 $0.00902
Sonnet 5.5 $0.00451 $0.00451
Haiku 4.5 $0.00226 $0.00226

Measured 2mo ago against content hash 51ab2d76441e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ClueArk AGENTS.md 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 2mo 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.

AGENTS.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ClueArk 协作说明

本文档归纳仓库布局、部署与本地开发的常用入口。完整功能说明见 README.md（英文）、README_ZH.md（中文）；爬虫服务见 crawler/README.md。

概述

ClueArk（线索方舟）：面向个人与团队的 AI 情报聚合平台。围绕话题监控聚合 RSS/Atom、网页列表（独立爬虫）、JSON 热点 API 等公开信源；可选接入 DeepSeek 兼容 API 做条目富化、OpenAI 兼容 Embeddings 做语义匹配与相似报道聚类。技术栈：React 18 + TypeScript + Vite（前端）、NestJS + MongoDB（Mongoose）（主 API）、独立 NestJS 爬虫服务（Cheerio）、Docker Compose 部署。

仓库结构

路径 说明
frontend/ 用户 Web 前端（Vite + React）
admin-web/ 独立运营后台（Vite + React + Ant Design；仅 admin 登录）
backend/ 主 HTTP API（NestJS）；运营能力在 /api/admin/*
crawler/ Web 列表页爬虫服务，与主站契约对齐上报
data/ 内置信源种子等（如 built-in-catalog.json）
docker-compose.yml 推荐部署入口：MongoDB + backend + web + admin-web + crawler
.env.example 根目录 Compose 环境变量模板（复制为 .env）
backend/.env.example、crawler/.env.example 本地开发参考

后端模块（backend/src/modules/）

  • feed-items/ — 条目、采集 ingest、RSS/热点等管线（无用户向列表 API）
  • sources/ — 统一信源池；RSS/热点轮询由 worker 内 SourcePollScheduler 调度
  • worker-scheduler/ — 仅 worker 进程：@Cron（信源轮询、快照/Brief 入队、相似聚类维护）
  • monitors/ — 话题监控、monitor_snapshots 物化读模型
  • vector-store/ — Qdrant 向量 upsert/search（禁止 HTTP 读路径做余弦）
  • queue/ — BullMQ 流水线；worker 容器（node dist/worker）消费
  • notifications/ — 匹配通知（站内）
  • monitor-pipeline/ — ingest 后 embed → match → notify
  • llm/ — 条目富化（enrich_llm 队列；仅监控信源经 pipeline 入队，无 Cron 扫全库）
  • aggregation-policy/ — 聚合策略
  • admin/、auth/、users/ — 管理与认证

爬虫实现在 crawler/src/（按 nextPollAt 拉取 Web 信源，详见 crawler/README.md）。

架构约束（监控优先）

  1. Mongo 仅存业务字段，不存 simEmbed* / descriptionEmbedding 等向量数组。
  2. 相似检索 仅经 VectorStoreService → Qdrant；HTTP 读 API 禁止 cosineSimilarity。
  3. 通知路径：新条目（仅 monitoredByCount > 0 信源）→ pipeline:process_new_item → 站内通知；不等待 LLM 富化。
  4. 列表/研判：GET /monitors 读 monitor_snapshots；GET /monitors/:id/intelligence 禁止同步全量打分。
  5. Compose 栈：mongodb + redis + qdrant + worker（必须先就绪；Cron + BullMQ 消费）+ backend（HTTP + 入队，无 @Cron）+ web（用户产品）+ admin-web（运营后台）+ crawler。
  6. 启动校验：REDIS_URL、QDRANT_URL、FEED_EMBEDDING_API_KEY、DEEPSEEK_API_KEY 必填；Mongo/Redis/Qdrant 连不上则进程退出；API 启动前等待 worker Redis 心跳。本地 npm run dev 同时起 API 与 worker。
  7. 前端：用户产品默认 /app/monitors；运营后台为独立 SPA（admin-web/，POST /api/admin/auth/login）。主站已移除 embedded /app/admin/*。

Read the full file on GitHub · 107 lines

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. 2mo ago First seen · 107 lines · 2,255 tokens per session scan A 51ab2d76441e

Subscribe to this mod's changes

ClueArk AGENTS.md is an instructions file published in the GitHub repository lqomg/ClueArk (53 stars, last pushed 3mo ago), licensed MIT. It adds 2,255 tokens to every session, about $0.0090 per session on Opus 5.5. 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.

Related

ClueArk AGENTS.md compared with instructions from other repositories

ClueArk AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ClueArk AGENTS.mdlqomg/ClueArkInstructions file533mo agoMITA2,255Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode