holoscrape-mcp: Instructions file for Claude Code

CLAUDE.md

holoscrape-mcp CLAUDE.md is an instructions file for Claude Code from joshghal/holoscrape-mcp. It costs 1,620 tokens per session, scanned A, original, MIT.

Project instructions for holoscrape-mcp, a standalone server that connects Claude Code to the HoloScrape browser extension. They describe its tools, testing, credentials, and release process.

In plain words
What is it for?
Maintaining the server's tool descriptions and matching implementation, checking changes with the extension's tests, and following its npm release workflow.
Why use it?
They help keep the server and extension aligned, preserve credential boundaries, and prevent unrequested publishing or repository changes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is joshghal/holoscrape-mcp's own configuration. It tells Claude Code how to work on holoscrape-mcp 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 holoscrape-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to joshghal/holoscrape-mcp. 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/joshghal/holoscrape-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/joshghal/holoscrape-mcp

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 holoscrape-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/joshghal/holoscrape-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/joshghal/holoscrape-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,620 This file is loaded in full into every session.
When invoked 1,620 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 $0.01620 $0.01620
Opus 5.5 $0.00648 $0.00648
Sonnet 5.5 $0.00324 $0.00324
Haiku 4.5 $0.00162 $0.00162

Measured 1mo ago against content hash b8700d1a31e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

holoscrape-mcp 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 1mo 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 · 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.

CLAUDE.md — holoscrape-mcp (standalone MCP server)

This is the public, npm-published half of HoloScrape. The other half — the Chrome MV3 extension the server talks to — lives in the private repo joshghal/holoscrape at ~/Documents/personal/ideation/holoscrape.

Rule: index.mjs here and holoscrape/mcp/index.mjs in the extension repo must stay byte-identical. Any change to one must be applied to the other in the same task, verified with diff. The extension repo's test suite is what exercises this server — run npm test over there after touching index.mjs here.

Publishing: users get this via npx -y holoscrape-mcp from the npm registry. Local edits reach nobody until commit → push → version bump → npm publish (the user supplies the OTP). Never publish, commit, or push without the user explicitly asking.

Communication

Explain changes in tables and bullet points, not paragraph prose.

Tool descriptions are the product, not documentation

This file is where every tool's description text lives, and those descriptions are the only thing steering the model that calls them. Write them as decision procedures for a model, not as API reference prose:

  • say WHEN to reach for the tool and when NOT to (the "Best for: / Not recommended for:" shape);
  • name the field to read before trusting a result (looksLikeFurniture, distinctness, containerRows) and say what a misleading value looks like;
  • prefer teaching the model to choose over adding a special case to the engine. Capability goes in the code generically; the knowledge of when to use it goes in the description.

Corollary: no site-specific logic in the server or engine. Per-app facts (where an app hides its store, how it paginates) live in the extension's providers.js descriptors as DATA. A tool that branches on a hostname is a bug in this architecture.

Never tune a test to get green

A red test means the logic is wrong — change the logic until the ORIGINAL assertion passes. Never loosen an assertion, skip a case, soften a fixture, or special-case test input in production code. If a test genuinely asserts wrong behaviour, say so and get agreement before editing it; never quietly edit it and report "all green."

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. 1mo ago Changed · +8 lines · +167 tokens per session b8700d1a31e4
  2. 2mo ago First seen · 99 lines · 1,453 tokens per session scan A 354f9f8b5406

Subscribe to this mod's changes

holoscrape-mcp CLAUDE.md is an instructions file published in the GitHub repository joshghal/holoscrape-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,620 tokens to every session, about $0.0065 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.

Related

holoscrape-mcp CLAUDE.md compared with instructions from other repositories

holoscrape-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
holoscrape-mcp CLAUDE.mdjoshghal/holoscrape-mcpInstructions file01mo agoMITA1,620Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283kyesterdayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot