What is optifeed-radar CLAUDE.md?

Project instructions for Optifeed Radar, an open-source checker that asks several AI services whether they recommend a brand to potential buyers. It includes a command-line tool and an MCP server, and runs locally with your own API keys.

It guides work on the radar's modules, commands, layout, shopping checks for named products, and messaging rules. It also points agents to the authoritative development plan before they change code.

It prevents coding agents from implementing deferred features or using wording that conflicts with the project's current scope and tests.

How optifeed/optifeed-radar configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to optifeed/optifeed-radar. 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/optifeed/optifeed-radar/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/optifeed/optifeed-radar

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/optifeed/optifeed-radar/claude-md/github.svg)](https://agentmods.dev/instructions/optifeed/optifeed-radar/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/optifeed/optifeed-radar/claude-md"><img src="https://agentmods.dev/badge/instructions/optifeed/optifeed-radar/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/optifeed/optifeed-radar/claude-md"><img src="https://agentmods.dev/badge/instructions/optifeed/optifeed-radar/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,446 This file is loaded in full into every session.

When invoked 2,446 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.

Model	Per session	Once invoked
Fable 5.1	$0.02446	$0.02446
Opus 5.5	$0.00978	$0.00978
Sonnet 5.5	$0.00489	$0.00489
Haiku 4.5	$0.00245	$0.00245

Measured 2mo ago against content hash 86cd0c642088, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

optifeed-radar 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 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.

CLAUDE.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Optifeed Radar

Open-source AI visibility checker: CLI + MCP server that asks real AI engines (OpenAI, Gemini, Perplexity, Claude) real buyer questions and scores whether a brand gets recommended. Runs locally, BYO API keys, MIT.

Scope (revised 2026-07-18, revision 2): the launch build is M0-M11 + M12a + M15-M17. M12a (Shopping-lite: shopping <domain> --products, manually named products only) is IN and shipped. Still DEFERRED: M12b (catalog/feed discovery adapters), M13 (protocol spike), M14 (lint-feed). Do not implement, stub, or scaffold M12b/M13/M14; M13/M14 were built and then removed on 2026-07-17 (recoverable at faf351f), do not reintroduce them. Copy rule that follows from this: the products a user NAMES are present tense; catalog/feed discovery and ACP/UCP feed linting stay FUTURE tense with a waitlist link (enforced by test/copy/messaging-rules.ts).

The module plan is authoritative and lives in the docs repo: /Users/erdem/workspace/optifeed-radar-docs/dev-plan.md (modules M0-M17 + the Global decisions section - read it before writing any code; it carries the same scope revision). If that path is not accessible in your session, ask before proceeding - do not guess module scope. TASKS.md lives in the same docs repo and tracks status only (it moved out of this repo on 2026-07-23, so the published package carries no internal build tracker). Implement one module per session unless told otherwise. Where this file and the plan disagree, the plan wins. Fuller product strategy and the messaging guide live in /Users/erdem/workspace/optifeed-radar-docs/source-of-truth.html.

Commands

npm run check           # typecheck + lint + test - the pre-commit gate
npm run typecheck       # tsc --noEmit
npm test                # vitest run
npm test -- <pattern>   # a single test file
npm run format:check    # prettier --check (also part of the gate)
npm run build           # tsc -p tsconfig.build.json -> dist/
npm run dev -- <args>   # tsx src/cli/index.ts <args>  (e.g. audit example.com)

Read the full file on GitHub · 168 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.

2mo ago First seen · 168 lines · 2,446 tokens per session scan A 86cd0c642088

Subscribe to this mod's changes

optifeed-radar CLAUDE.md is an instructions file published in the GitHub repository optifeed/optifeed-radar (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,446 tokens to every session, about $0.0098 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 2026-08-31.

Marketing and SEO agent-skills agentic-commerce ai-shopping ai-visibility answer-engine-optimization chatgpt

optifeed-radar CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
optifeed-radar CLAUDE.mdoptifeed/optifeed-radar	Instructions file	5	3mo ago	MIT	A	2,446	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	280k	2d ago	MIT	A	4,325	Codex, OpenCode

optifeed-radar: Instructions file for Claude Code