agentmods.dev

omnireach: Instructions file for Claude Code

CLAUDE.md

omnireach CLAUDE.md is an instructions file for Claude Code from Daily-AC/omnireach. It costs 11,688 tokens per session, scanned C, original, MIT.

Project guidance for omnireach, a command-line project that searches for web sources and fetches their full text. Its repository contains related search and fetching commands in one codebase, known as a monorepo.

In plain words
What is it for?
Use it when changing omnireach’s search or fetch commands, understanding its source adapters and tiers, or deciding where new functionality belongs.
Why use it?
It gives coding agents the project’s purpose, architecture, terminology, and development decisions in one automatically loaded reference.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is Daily-AC/omnireach's own configuration. It tells Claude Code how to work on omnireach 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 omnireach configures →

not rated 19repo changed 5d ago C scan 11,688 tokens original MIT
View source ↗ Daily-AC/omnireach
Reuse

Borrowing it

Nothing to install: this file belongs to Daily-AC/omnireach. 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/Daily-AC/omnireach/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Daily-AC/omnireach

Made for: Claude Code.

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 omnireach CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/daily-ac/omnireach/claude-md/github.svg)](https://agentmods.dev/instructions/daily-ac/omnireach/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/daily-ac/omnireach/claude-md"><img src="https://agentmods.dev/badge/instructions/daily-ac/omnireach/claude-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 omnireach CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/daily-ac/omnireach/claude-md"><img src="https://agentmods.dev/badge/instructions/daily-ac/omnireach/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11,688 This file is loaded in full into every session.
When invoked 11,688 The same file — it is already loaded in full.
Security scan C 2 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 $0.11688 $0.11688
Opus 5 $0.05844 $0.05844
Sonnet 5 $0.02338 $0.02338
Haiku 4.5 $0.01169 $0.01169

Measured 5d ago against content hash 08587995fdbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

omnireach CLAUDE.md scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- `v0.11.0-alpha` (2026-06-22): **对外定位重写 (Senses/Eyes) + AI-native 安装** — 把面向陌生人/agent 的第一屏从"补中转站 WebSearch"(冰山一角)重写成 **"give your agent the senses of a logged-in human across the whole internet"**(冰山主体: search + read 15

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `v0.11.0-alpha` (2026-06-22): **对外定位重写 (Senses/Eyes) + AI-native 安装** — 把面向陌生人/agent 的第一屏从"补中转站 WebSearch"(冰山一角)重写成 **"give your agent the senses of a logged-in human across the whole internet"**(冰山主体: search + read 15
CLAUDE.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — omnireach 项目协作上下文

This file is loaded automatically when Claude Code starts in this repo. It carries omnireach project knowledge that previously lived in user-global memory; centralizing it here lets the context follow the repo across machines and sessions.

项目是什么

omnireach 是项目名, 同 repo 内多个职责子命令 (subcommand 形态, 落地后再判断要不要拆 binary), 不是单一工具。完整"触达全网"语义由三层职责实现, 都在同 repo（不开 sister repo, 拍板于 2026-05-27 session）:

  • omnireach search (v0.1+ 起在用): search 层 — 全网定位 metadata + URL, 不取内容
  • omnireach fetch (v0.10 起 ship 为 subcommand): fetch 层 — 给定 URL 取全文 markdown; 当前 host-aware 路径为普通网页内置 HTTP → Jina fallback，mp.weixin.qq.com → OpenCLI 后台临时 tab；Crawl4AI 只保留显式 opt-in
  • parse (暂未实现): parse 层 — 视频/音频内容解析 (字幕/STT/逐帧), 真有 issue 才加

类比 cargo (一个 repo 下 cargo / rustc / rustfmt 多个 sibling binary, 共享一个项目愿景) 而不是 git + git-lfs (后者是 standalone separate repo)。Why monorepo 而非 multirepo: 2026-05-27 session 调研 Crawl4AI 时验证 —— 收纳 crwl 作为 fetch 工具不影响 search 行为, 只补齐 search 结果, 完全没有 sister repo 的耦合协调成本。一个 release 频道 + 一个 issue tracker + 一份 README 就够。

search binary 名是否改名: 曾经考虑改成 omnisearch 因为"reach 是触达, search 只是触达的第一步" — 2026-05-27 拍板不改。Rationale: v0.10 ship 了 omnireach fetch 后, omnireach 这个名字反而契合 umbrella 定位 —— omnireach search (触达 = 找) + omnireach fetch (触达 = 取) 都是 reach 的合理子动作, subcommand 分担具体语义, 项目名留给愿景。改名得不偿失。

本 repo 当前覆盖 search (v0.1+) + fetch (v0.10+) 两层。用户问"加 parse 能力到 omnireach 里"时按"等本 repo 加 sibling subcommand/binary, 不开 sister repo"处理; 视频解析这类大依赖立项前先看真 issue (YAGNI)。见下方"架构边界"。

目标用户与痛点

omnireach 是给任何 Claude Code WebSearch 拿不到结果的用户的工具 — 受众比"中转站"宽得多。

WebSearch 是 server tool (web_search_20250305), 真实可用性其实经过两层 gate, 受影响场景不同根因不同:

1. 客户端 gate (WebSearchTool.isEnabled() + getAPIProvider() 看 CLAUDE_CODE_USE_* env var):

  • 默认 firstParty (没设 CLAUDE_CODE_USE_*, 即便只改了 ANTHROPIC_BASE_URL 也归这类) → tool 注册
  • 显式 CLAUDE_CODE_USE_BEDROCK=1 → 关
  • 显式 CLAUDE_CODE_USE_VERTEX=1 + Claude 4+ → 注册; 老 Claude → 关
  • 显式 CLAUDE_CODE_USE_FOUNDRY=1 → 注册

Read the full file on GitHub · 231 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. 5d ago Changed · +36 lines · +2,585 tokens per session 08587995fdbd
  2. 9d ago First seen · 195 lines · 9,103 tokens per session scan C e1f9a676f6ef

Subscribe to this mod's changes

omnireach CLAUDE.md is an instructions file published in the GitHub repository Daily-AC/omnireach (19 stars, last pushed 5d ago), licensed MIT. It adds 11,688 tokens to every session, about $0.0584 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude CodeResearchagent-toolsai-agentsbilibilidouyinllm-tools
Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,737 tokens