What is claude_code_gmail_plugin CLAUDE.md?

Project instructions for a Claude Code plugin that analyzes Gmail messages and organizes them with labels.

They guide email classification, Gmail searches, label creation or removal, automatic tagging, and sender analysis.

They explain how the plugin, Gmail connection, helper scripts, and standalone command-line program fit together.

claude_code_gmail_plugin CLAUDE.md — Instructions file by axisrow

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/axisrow/claude_code_gmail_plugin/claude-md

Clone the repo

git clone --depth 1 https://github.com/axisrow/claude_code_gmail_plugin

Per session 887 This file is loaded in full into every session.

When invoked 887 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00887	$0.00887
Opus 5	$0.00443	$0.00443
Sonnet 5	$0.00177	$0.00177
Haiku 4.5	$0.00089	$0.00089

Measured yesterday against content hash 1e7068a5b08a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude_code_gmail_plugin 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 yesterday.

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 · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 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.

Project Overview

Claude Code plugin for Gmail email analysis. Extends Gmail MCP with 5-category classification, auto-tagging, search, and label management. Also includes standalone CLI (main.py) using Claude Agent SDK.

Two modes of operation:

Plugin (skills) — works inside Claude Code session via Gmail MCP tools + helper scripts
Standalone CLI (main.py) — runs outside Claude Code via Claude Agent SDK (cannot run inside Claude Code due to nested session restriction)

Plugin Architecture

.claude-plugin/plugin.json     # plugin manifest ("gmail-analyzer")
skills/
  analyze-emails/SKILL.md      # 5-category email classification
  search-emails/SKILL.md       # Gmail query search
  manage-labels/SKILL.md       # label CRUD
  auto-tag/SKILL.md            # analyze + apply labels with confirmation
scripts/
  modify_labels.py             # apply label changes (stdin JSON)
  create_label.py              # create label (CLI arg)
  delete_label.py              # delete label (CLI arg)
  top_senders.py               # sender analytics (CLI args)

Skills ↔ MCP ↔ Scripts

Skills use Gmail MCP tools for read operations:

gmail_search_messages, gmail_read_message, gmail_list_labels

Skills use scripts (via Bash) for write operations not available in MCP:

modify_labels.py — add/remove labels from messages
create_label.py / delete_label.py — label CRUD

Scripts communicate via JSON (stdin/stdout) and import gmail_client.py via sys.path.

Email categories

🟢 Personal / Личное
🔵 Useful Newsletter / Полезная рассылка
🟡 Important Notification / Важное уведомление
🟠 Noise / Шум
🔴 Spam / Мусор

Tagging JSON format

{"actions": [{"message_id": "...", "add": ["Label_ID"], "remove": ["Label_ID"]}]}

gmail_client.py

Gmail API client with three backends (auto-selected): gcloud ADC → gws CLI → credentials.json.

Read the full file on GitHub · 97 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.

yesterday First seen · 97 lines · 887 tokens per session scan A 1e7068a5b08a

Subscribe to this mod's changes

claude_code_gmail_plugin CLAUDE.md is an instructions file published in the GitHub repository axisrow/claude_code_gmail_plugin (3 stars, last pushed 5mo ago), licensed MIT. It adds 887 tokens to every session, about $0.0044 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.

Planning Productivity Research

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 · 5,182 tokens

buildNext

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

claude_code_gmail_plugin CLAUDE.md