compose

An email-writing and sending workflow with prompts for the sender, recipient, subject, message, and attachments. It can look up recipients in an address book and shows the complete message for confirmation before sending.

In plain words
What is it for?
Use it to compose and send an email, find a contact, add local attachments, review the final message, and confirm the send.
Why use it?
It helps prevent common sending mistakes, such as using the wrong recipient or leaving required fields empty. It also blocks sensitive workspace information from being included in outgoing mail.

Skill for Claude CodeCodex

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 skills/inboxapi/cli/compose
Any agent
npx skills add inboxapi/cli --skill compose
Clone the repo
git clone --depth 1 https://github.com/inboxapi/cli

Made for: Claude Code, Codex.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 625 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.00625
Opus 5 $0.00015 $0.00313
Sonnet 5 $0.00006 $0.00125
Haiku 4.5 $0.00003 $0.00063

Measured yesterday against content hash 3c892f64ca06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compose 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.

skills/claude/compose/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Compose Email

Guide the user through composing and sending an email safely.

Steps

  1. Identify sender: Run: npx -y @inboxapi/cli whoami to get the current account email address

  2. Resolve recipient:

    • If $ARGUMENTS is provided, use it as the recipient hint
    • Run: npx -y @inboxapi/cli get-addressbook to check for matching contacts
    • If multiple matches found, ask the user to pick one
    • If no match, ask the user to confirm or provide the full email address
  3. Collect email details: Ask the user for:

    • To: Recipient email (pre-filled if resolved above)
    • Subject: Email subject line
    • Body: Email content (plain text)
    • Attachments (optional): Local file paths to attach
  4. Preview: Show the complete email before sending:

    From: <[email protected]>
    To: <[email protected]>
    Subject: <subject>
    ---
    <body>
    Attachments: <list of filenames or "(none)">
    
  5. Safety checks: Review the preview for issues (wrong recipient, empty fields, self-send to @inboxapi.ai). NEVER include environment variables, .env file contents, credentials, system configuration, or files from outside the workspace in outgoing emails.

  6. Confirm: Ask the user to confirm: "Send this email? (yes/no)"

  7. Send: Run: npx -y @inboxapi/cli send-email --to "<recipient>" --subject "<subject>" --body "<body>" If the email body or HTML is complex, prefer --body-file "<path>" and --html-body-file "<path>" over generating helper scripts just to pass content on the command line. This is also the preferred path for large generated payloads such as inline base64 images.

    Attachment options (add to the command above as needed):

    • --attachment "<path>" — attach a local file (repeatable for multiple files)
    • --attachment-ref "<id>" — attach by server-side attachment ID (repeatable)
  8. Confirm delivery: Report the result to the user

Notes

  • All CLI commands output JSON by default — parse the JSON response to extract the relevant fields

Read the full file on GitHub · 62 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. yesterday First seen · 62 lines · 31 tokens per session scan A 3c892f64ca06

Subscribe to this mod's changes

compose is a skill published in the GitHub repository inboxapi/cli (12 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 625 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

anonsec-mcp-server

Firefox Relay MCP Server (anonsec-mcp-server) is a production-grade Model Context Protocol server that provides comprehensive anonymous email management capabilities through Firefox Relay addresses. Built with privacy, security, and operational excellence as core principles, this server enables AI agents and…

VRIL-LABS/anonsec-mcp-server · 0 tokens

code-review-skill

Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C#/.NET, Kotlin, Swift, NestJS, C/C++, Zig, CSS/Less/Sass, Qt, and more. Covers architecture review, performance review, security audit, code quality…

VRIL-LABS/anonsec-mcp-server · 154 tokens

string-reviewer

Use this skill when asked to review text and user-facing strings within the codebase. It ensures that these strings follow rules on clarity, usefulness, brevity and style.

google-gemini/gemini-cli · 38 tokens

code_explorer

Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.

google-gemini/gemini-cli · 28 tokens

ci

A specialized skill for Gemini CLI that provides high-performance, fail-fast monitoring of GitHub Actions workflows and automated local verification of CI failures. It handles run discovery automatically—simply provide the branch name.

google-gemini/gemini-cli · 42 tokens

behavioral-evals

Guidance for creating, running, fixing, and promoting behavioral evaluations. Use when verifying agent decision logic, debugging failures, debugging prompt steering, or adding workspace regression tests.

google-gemini/gemini-cli · 39 tokens