wasp-mcp: Instructions file for Claude Code

CLAUDE.md

wasp-mcp CLAUDE.md is an instructions file for Claude Code from sfeeney1897/wasp-mcp. It costs 6,995 tokens per session, scanned A, original, MIT.

A set of project instructions for AgentManifest, a Firefox extension that lets AI agents search webpages through a small index of headings and sections, then retrieve only the relevant text.

In plain words
What is it for?
It is for understanding the project’s goals, file layout, browser-extension setup, and WASP, the protocol used to describe and query webpage structure.
Why use it?
It helps an agent find useful page information without sending an entire webpage or its raw HTML to a language model.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is sfeeney1897/wasp-mcp's own configuration. It tells Claude Code how to work on wasp-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 wasp-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sfeeney1897/wasp-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/sfeeney1897/wasp-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sfeeney1897/wasp-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 wasp-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sfeeney1897/wasp-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/sfeeney1897/wasp-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sfeeney1897/wasp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sfeeney1897/wasp-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 wasp-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sfeeney1897/wasp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/sfeeney1897/wasp-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,995 This file is loaded in full into every session.
When invoked 6,995 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 $0.06995 $0.06995
Opus 5 $0.03497 $0.03497
Sonnet 5 $0.01399 $0.01399
Haiku 4.5 $0.00700 $0.00700

Measured 9d ago against content hash 9ed1220568a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wasp-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 9d 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 · 563 lines

How it starts

The opening of the file, as written. The whole thing — 563 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentManifest — WASP (Web Agent Semantic Protocol)

Firefox browser extension that makes any webpage instantly queryable by an AI agent. Instead of scraping the full DOM or sending raw HTML to an LLM, WASP generates a lightweight structural index (the manifest) and fetches live content for only the sections relevant to a query. The result is fast, token-efficient, structure-aware retrieval over arbitrary webpages.

Hackathon: LAHACKS 2026 / Cognition AI Challenge — "Smarter context retrieval" track.


Project Vision

The core insight is that webpages have two layers of useful information:

  1. Structure — headings, sections, and anchors that form a table of contents. This is cheap to index and small enough to pass to an LLM as context.
  2. Content — the actual text under each heading. This is expensive to send in full, and most of it is irrelevant to any given query.

WASP exploits this by making the structure the primary artifact (the manifest) and treating content as a lazy resource fetched only when needed. An agent can read the manifest, decide which sections are relevant, and request only those. This is an index, not a copy.

A secondary goal is a standard protocol: if a site publishes its own /.well-known/wasp.json, agents can skip DOM parsing entirely and trust the site's own semantic description of itself. Client-generated fallback handles every other site.


Loading the Extension

about:debugging → This Firefox → Load Temporary Add-on → select manifest.json

After loading, click the W toolbar icon to open the sidebar. The extension auto-injects into already-open tabs via browser.scripting.executeScript — no manual page reload needed. Content scripts declared in manifest.json auto-inject into new tabs.


File Map

manifest.json            Firefox MV3 declaration
content.js               DOM interface — runs in every page context
background.js            Service worker — coordinator, LLM proxy, state store
providers.js             ES module — claude / openai / ollama / devin adapters
sidebar/
  sidebar.html           Extension sidebar UI (dark theme, inline CSS)
  sidebar.js             Sidebar logic — port messaging, streaming render, citations
styles/
  highlight.css          .agent-manifest-highlight — injected into every page
icons/
  icon-48.png
  icon-96.png

Read the full file on GitHub · 563 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. 9d ago First seen · 563 lines · 6,995 tokens per session scan A 9ed1220568a3

Subscribe to this mod's changes

wasp-mcp CLAUDE.md is an instructions file published in the GitHub repository sfeeney1897/wasp-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 6,995 tokens to every session, about $0.0350 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.

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 · 3,735 tokens