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 instructions/lqomg/clueark/agents-mdgit clone --depth 1 https://github.com/lqomg/ClueArkWrote 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/instructions/lqomg/clueark/agents-md)<a href="https://agentmods.dev/instructions/lqomg/clueark/agents-md"><img src="https://agentmods.dev/badge/instructions/lqomg/clueark/agents-md.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 | $0.02255 | $0.02255 |
| Opus 5 | $0.01128 | $0.01128 |
| Sonnet 5 | $0.00451 | $0.00451 |
| Haiku 4.5 | $0.00226 | $0.00226 |
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 5d 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 — 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 → notifyllm/— 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）
- Mongo 仅存业务字段，不存
simEmbed*/descriptionEmbedding等向量数组。 - 相似检索 仅经
VectorStoreService→ Qdrant；HTTP 读 API 禁止cosineSimilarity。 - 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。 - 列表/研判：
GET /monitors读monitor_snapshots；GET /monitors/:id/intelligence禁止同步全量打分。 - 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。 - 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。 - 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/*。
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.
- 5d ago First seen · 107 lines · 2,255 tokens per session scan A 51ab2d76441e
ClueArk AGENTS.md is an instructions file published in the GitHub repository lqomg/ClueArk (52 stars, last pushed 1mo ago), licensed MIT. It adds 2,255 tokens to every session, about $0.0113 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).