Borrowing it
Nothing to install: this file belongs to elct9620/noon-sight. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/elct9620/noon-sight/main/CLAUDE.mdgit clone --depth 1 https://github.com/elct9620/noon-sightWrote 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/elct9620/noon-sight/claude-md)<a href="https://agentmods.dev/instructions/elct9620/noon-sight/claude-md"><img src="https://agentmods.dev/badge/instructions/elct9620/noon-sight/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.
<a href="https://agentmods.dev/instructions/elct9620/noon-sight/claude-md"><img src="https://agentmods.dev/badge/instructions/elct9620/noon-sight/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.05278 | $0.05278 |
| Opus 5 | $0.02639 | $0.02639 |
| Sonnet 5 | $0.01056 | $0.01056 |
| Haiku 4.5 | $0.00528 | $0.00528 |
Grade A, and why
noon-sight CLAUDE.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 8d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Purpose
noon-sight is an MCP server on Cloudflare Workers that aggregates what a site publishes and how it is read. Access is gated by Cloudflare Zero Trust.
Two kinds of question live here, and which one a source answers settles the shape of its tool before anything else about it is decided.
Traffic is quantitative. One event says nothing on its own; only the aggregate informs. So a traffic tool groups by a closed list of questions, counts, and answers for a period against the equally long one before it — the change is what makes a number worth reading. Analytics only ever meets someone who already arrived, Search Console counts the ones who were shown the site and did not come, and Cloudflare sits in front of the request and sees whoever asked, including everything that runs no JavaScript and so reaches neither.
Content is qualitative. One item carries the whole meaning and an aggregate destroys it: 8 posts about Ruby tells a reader nothing they did not already know, while the sentence that post actually made is the thing worth having. So a content tool returns the content itself within a window and leaves the reading to whoever asked. Counting is not withheld from them — it is theirs to do, on the text they now hold.
A source earns its place by answering what the others structurally cannot. Counting what should have been read, or returning what should have been counted, is the one mistake no amount of care downstream repairs.
Minimal by design. Implement only the tool being asked for. Feature completeness is not the goal; staying small is. Before adding an abstraction layer, a config knob, or code for a case that might come later, confirm it is needed now.
No SPEC.md. Correctness is expressed by vitest tests, not by specification documents.
Working together
Work runs in two movements, and the boundary between them carries more weight than the commands do.
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.
- 8d ago First seen · 143 lines · 5,278 tokens per session scan A f4a2ed551b85
noon-sight CLAUDE.md is an instructions file published in the GitHub repository elct9620/noon-sight (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 5,278 tokens to every session, about $0.0264 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 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).
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).
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.
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.