What is inbox-to-action CLAUDE.md?

Project instructions for a command-line tool that reviews unread email, classifies and summarizes messages, extracts tasks, drafts replies, and flags calendar items. It never sends email.

They are for running or testing inbox triage, authentication, the local MCP server, mock mode, draft generation, and integrations with calendar or task tools.

They give the coding agent the project's commands, layout, testing expectations, and security rule that Gmail access must remain read-only plus draft creation.

How tarunlnmiit/inbox-to-action configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tarunlnmiit/inbox-to-action. 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/tarunlnmiit/inbox-to-action/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tarunlnmiit/inbox-to-action

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/tarunlnmiit/inbox-to-action/claude-md/github.svg)](https://agentmods.dev/instructions/tarunlnmiit/inbox-to-action/claude-md)

Your own site

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

Per session 826 This file is loaded in full into every session.

When invoked 826 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	$0.00826	$0.00826
Opus 5	$0.00413	$0.00413
Sonnet 5	$0.00165	$0.00165
Haiku 4.5	$0.00083	$0.00083

Measured 10d ago against content hash 1a918b0d2016, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

inbox-to-action 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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — project context for Claude Code

One-pass agentic inbox triage: fetch unread mail → classify → summarize → extract tasks → draft replies (never sends) → flag calendar → write triage-report.md.

Commands

inbox-to-action run --since 24h [--no-drafts] [--max N] [--telegram] [--todoist] [--config PATH] [--mock]
inbox-to-action auth [--account <id>] [--config PATH] [--client-secrets PATH]
inbox-to-action mcp                      # stdio MCP server (also: python -m inbox_to_action.mcp_server)
pytest --cov=.                           # tests (LLM + Gmail mocked)
ruff check inbox_to_action/

Security invariant (do not break)

Gmail scopes = gmail.readonly + gmail.compose ONLY. No send scope, no send call anywhere. Drafts only. Enforced by tests/test_gmail.py. --mock never writes to real Gmail.

Package layout

inbox_to_action/
  main.py          Typer CLI (run/auth/mcp)
  agent.py         per-email trajectory (classify→summarize→tasks→draft→calendar)
  llm_client.py    providers: claude, ollama, openrouter, nim, openai, anthropic, host
  reasoner.py      ProviderReasoner vs HostReasoner injection seam
  config.py        Settings: triage_instructions, rules[], accounts[]
  models.py        Email, Task, TriageResult, CATEGORIES
  report.py        triage-report.md renderer
  mcp_server.py    FastMCP: fetch_emails, save_gmail_draft, append_tasks, write_report
  mailboxes/       MailAccount protocol; gmail.py (multi-account Gmail/Workspace)
  tools/           classifier, summarizer, tasks (+ Todoist), gmail (+ is_noreply),
                   calendar_flag, notify (Telegram)
  fixtures/        sample_inbox.json (--mock)

Config & env

config.json (gitignored; example: config.example.json): triage_instructions, rules[] (field: sender|subject|body|any → category), accounts[] (id, kind: gmail, label, client_secret?).
.env (gitignored; example: .env.example): PROVIDER, MODEL, provider keys (OPENROUTER_API_KEY, OPENAI_API_KEY, NIM_API_KEY/NVIDIA_API_KEY, ANTHROPIC_API_KEY, OLLAMA_BASE_URL), TRIAGE_INSTRUCTIONS, INBOX_TO_ACTION_CONFIG, TODOIST_API_TOKEN, TELEGRAM_BOT_TOKEN/TELEGRAM_TOKEN
- TELEGRAM_CHAT_ID, GMAIL_CLIENT_SECRETS, INBOX_TO_ACTION_TOKEN, INBOX_TO_ACTION_HTTP_TIMEOUT.

Read the full file on GitHub · 69 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.

10d ago First seen · 69 lines · 826 tokens per session scan A 1a918b0d2016

Subscribe to this mod's changes

inbox-to-action CLAUDE.md is an instructions file published in the GitHub repository tarunlnmiit/inbox-to-action (2 stars, last pushed 1mo ago), licensed MIT. It adds 826 tokens to every session, about $0.0041 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.

Claude Code Productivity ai-agent email-automation email-triage gmail llm-agent

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

inbox-to-action: Instructions file for Claude Code