evite-mcp: Instructions file for Claude Code

CLAUDE.md

evite-mcp CLAUDE.md is an instructions file for Claude Code from chrischall/evite-mcp. It costs 4,833 tokens per session, scanned A, original, MIT.

A set of project instructions for working on an Evite connection. It explains how the code is organized, how sign-in works, and which Evite actions are available.

In plain words
What is it for?
Use it when developing the Evite integration, especially when handling login, browser sessions, read actions, or write actions that require confirmation.
Why use it?
It gives a coding assistant the repository-specific context needed to change or maintain the project correctly. Evite has no public API, so the instructions also explain its session-based access.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions CLAUDE.md.

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chrischall/evite-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/evite-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,833 This file is loaded in full into every session.
When invoked 4,833 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 $0.04833 $0.04833
Opus 5.5 $0.01933 $0.01933
Sonnet 5.5 $0.00967 $0.00967
Haiku 4.5 $0.00483 $0.00483

Measured 10d ago against content hash 6b2d60c441a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evite-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 10d 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 · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 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.

TL;DR

MCP server for Evite event management — talks to evite.com's internal /services/ (and /ajax/, /tsunami/) API using the session cookies a signed-in browser holds (Evite has no public API). Cookie-session archetype.

6 read tools + 13 confirmed write tools (plus evite_upload_slots, read-only, and evite_healthcheck). Writes ask the user to confirm first — an elicitation prompt where the client supports one (and MCP_CONFIRM_ELICITATION isn't off), otherwise a preview + single-use confirmToken (MCP_CONFIRM_MODE) — and mutate only once confirmed.

Three auth tiers, in priority order:

  1. EVITE_EMAIL + EVITE_PASSWORD — headless form login (POST /ajax_login). Preferred / documented default.
  2. EVITE_SESSION_COOKIE — a raw cookie: header pasted from a signed-in evite.com tab (or set in CI). Used verbatim.
  3. fetchproxy bootstrap — lifts the session out of the user's already-signed-in evite.com browser tab via a one-shot WebSocket bridge.

Auth resolution

src/auth.ts — resolveSession(): the three-path priority resolver (Pattern A, "browser-bootstrap + Node-direct"). It produces a ResolvedSession = { cookieHeader, csrfToken? }:

  1. Tier-1 (preferred): if both EVITE_EMAIL and EVITE_PASSWORD are set → loginWithPassword() (src/auth-login.ts). One env var alone falls through.
  2. Tier-2: EVITE_SESSION_COOKIE → returned verbatim as cookieHeader (no CSRF token surfaced).
  3. Tier-3 (fallback): @fetchproxy/bootstrap opens a bridge to the signed-in tab, reads the declared cookies (x-evite-session, evtsession, x-evite-features, csrftoken — the declared key list is the security boundary), builds the cookie header in declaration order, and surfaces csrftoken as the CSRF token. Opt out with EVITE_DISABLE_FETCHPROXY=1.
  4. Nothing resolves → SessionNotAuthenticatedError with a hint naming the env-var escape hatches.

Read the full file on GitHub · 158 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. 10d ago Changed · +8 lines · +364 tokens per session 6b2d60c441a5
  2. 13d ago Changed · +4 lines · +111 tokens per session 86e6ab7dc5d5
  3. 1mo ago Changed · +84 tokens per session 90e4ded0d32f
  4. 1mo ago Changed · +69 tokens per session a4b048f0d723
  5. 1mo ago Changed · +15 tokens per session 64b0b587b339
  6. 1mo ago Changed · +84 tokens per session 5cd84b55dc25
  7. 1mo ago Changed · +36 tokens per session a06b1946435c
  8. 1mo ago Changed · +2 lines · +484 tokens per session ec95a6d1488d
  9. 1mo ago Changed · +160 tokens per session 69e4f3a44102
  10. 2mo ago First seen · 144 lines · 3,426 tokens per session scan A 78dbbfd70a4d

Subscribe to this mod's changes

evite-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/evite-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 4,833 tokens to every session, about $0.0193 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

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

evite-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
evite-mcp CLAUDE.mdchrischall/evite-mcpInstructions file02d agoMITA4,833Claude 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 file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot