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/gsd-build/agent-inbox/skillnpx skills add gsd-build/agent-inbox --skill skillgit clone --depth 1 https://github.com/gsd-build/agent-inboxWrote 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.
[](https://agentmods.dev/skills/gsd-build/agent-inbox/skill)<a href="https://agentmods.dev/skills/gsd-build/agent-inbox/skill"><img src="https://agentmods.dev/badge/skills/gsd-build/agent-inbox/skill.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00054 | $0.00846 |
| Opus 5 | $0.00027 | $0.00423 |
| Sonnet 5 | $0.00011 | $0.00169 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
agent-inbox 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 5d 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.
What it actually says
<when_to_use>
- Testing sign-up / auth flows that require email verification
- Receiving "confirm your account" or "verify your email" links
- Any automated workflow where you need to receive an email
- E2E testing of email-sending features </when_to_use>
mcp__agent-inbox__create_inbox— Create a new temporary inbox. Optionalnameparameter for easy reference.mcp__agent-inbox__check_inbox— Check for messages. Returns subjects, bodies, and extracted confirmation links.mcp__agent-inbox__wait_for_email— Poll until a matching email arrives. Filters byfromandsubject_contains. Auto-retries with backoff.mcp__agent-inbox__verify_email— One-shot: polls for confirmation email, extracts link, visits it via HTTP GET. Three steps in one call.mcp__agent-inbox__list_inboxes— List all active inboxes in this session.mcp__agent-inbox__delete_inbox— Delete an inbox when done.
Fast path (recommended) — use verify_email for the common case:
- Create inbox —
create_inbox({ prefix: "signup", name: "test" }) - Use the address — Enter it in a sign-up form, invite field, etc.
- Verify in one call —
verify_email({ address: "test", subject_contains: "confirm" })— polls for the email, extracts the link, visits it via HTTP. - Clean up —
delete_inbox({ address: "test" })
Manual path — when you need more control:
- Create inbox —
create_inbox({ prefix: "signup", name: "test" }) - Use the address — Enter it wherever the service asks for an email.
- Wait for email —
wait_for_email({ address: "test", from: "[email protected]", timeout_seconds: 60 })— polls with backoff until a matching email arrives. - Act on links — Navigate to the confirmation link via browser automation or HTTP.
- Clean up —
delete_inbox({ address: "test" })
<important_notes>
- Named inboxes: pass
nametocreate_inbox, then use that name in all other tools instead of the full email address. - Fallback providers: mail.tm is primary, 1secmail kicks in automatically if mail.tm is down.
- Inboxes are cleaned up automatically when the MCP server shuts down.
- Some services block disposable email domains. If sign-up is rejected, the service may have these domains on a blocklist. </important_notes>
1. create_inbox(prefix: "auth-test", name: "signup")
→ [email protected] (name: signup)
2. Fill sign-up form with that address + a password
3. verify_email(address: "signup", subject_contains: "confirm")
→ Email verified successfully!
HTTP Status: 200
Final URL: https://myapp.com/welcome
4. delete_inbox(address: "signup")
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.
- 5d ago First seen · 71 lines · 54 tokens per session scan A d93b71ad1776
agent-inbox is a skill published in the GitHub repository gsd-build/agent-inbox (61 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 846 once invoked, about $0.0003 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
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
browser-testing-with-devtools
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be…
designing-tests
Designs and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing infrastructure, debugging test failures, or when asked about unit tests, integration tests, or E2E testing.
qa/e2e-playwright
Playwright E2E 测试完整方法论,涵盖项目初始化、Page Object Model、认证复用、API Mock、视觉回归、多浏览器测试、CI 集成和调试技巧.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
backend/testing-guide
后端测试编写指南,包括单元测试、集成测试和E2E测试的编写方法和最佳实践.