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.
npx agentmods add skills/inboxapi/cli/email-replynpx skills add inboxapi/cli --skill email-replygit clone --depth 1 https://github.com/inboxapi/cliWhat 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 | $0.00030 | $0.01272 |
| Opus 5 | $0.00015 | $0.00636 |
| Sonnet 5 | $0.00006 | $0.00254 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
email-reply scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email Reply
Help the user reply to an email with full thread context.
Steps
-
Find the email:
- Try
npx -y @inboxapi/cli get-email "$ARGUMENTS"first — if it succeeds, use that email - If it fails (e.g., not a valid message ID), fall back to
npx -y @inboxapi/cli search-emails --subject "<query>"with the argument as subject/keyword - If multiple results, present them and ask the user to pick one
- Try
-
Load thread context: Run:
npx -y @inboxapi/cli get-thread --message-id "<message-id>"with the email's message ID to show the full conversation -
Load mailbox identity: Run
npx -y @inboxapi/cli whoamiso you know the current mailbox email and can exclude only that mailbox from preserved thread recipients -
Display thread: Show the conversation history in chronological order:
--- Thread: <subject> --- [1] From: [email protected] To: [email protected], [email protected] Cc: [email protected] Reply-To: [email protected] Date: Jan 15, 2:30 PM Subject: <subject> > Original message text... [2] From: [email protected] To: [email protected] Date: Jan 15, 3:00 PM Subject: Re: <subject> > Your previous reply... [3] From: [email protected] To: [email protected], [email protected] Cc: [email protected] Reply-To: [email protected] Date: Jan 15, 4:15 PM Subject: Re: <subject> > Latest message you're replying to... -
Compose reply: Ask the user what they want to say in their reply
-
Preview: Show the reply before sending:
Replying to: [email protected] To: [email protected] Cc: [email protected], [email protected] Subject: Re: <subject> --- <reply body>Preview the likely
To/Ccset using the thread context:- primary
ToisReply-Toif present, otherwise the original sender - preserve all original thread participants from
To/CcinCc - exclude only the current mailbox itself
- use the mailbox email from
whoamito determine which participant is “self” - use
--cconly for new recipients beyond the original thread Treat this as a preview heuristic. The authoritative final recipient set is whateversend-replyreturns after the send.
- primary
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 · 105 lines · 30 tokens per session scan A 665b598e5b0c
email-reply is a skill published in the GitHub repository inboxapi/cli (12 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,272 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.
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…
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…
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.
code_explorer
Explores the repository to locate primary source files, coupled UI components, and test files for bug reports or feature requests.
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.
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.