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/hashgraph-online/awesome-codex-plugins/mailagentnpx skills add hashgraph-online/awesome-codex-plugins --skill mailagentgit clone --depth 1 https://github.com/hashgraph-online/awesome-codex-pluginsWhat 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 | $0.00043 | $0.03323 |
| Opus 5 | $0.00022 | $0.01662 |
| Sonnet 5 | $0.00009 | $0.00665 |
| Haiku 4.5 | $0.00004 | $0.00332 |
Grade A, and why
mailagent 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MailAgent
MailAgent provides programmatic disposable inboxes for AI agents: receive OTP codes and magic links during signup flows, simulate inbound mail in CI, send/reply on verified domains, and diagnose timeouts.
Official docs: https://webmailagent.com/docs/agents.html
When to use
- Signup or login that sends a verification email
- Need OTP or magic link without hand-parsing HTML
- E2E / agent task: "register with a temp email"
- QA without real SMTP (
mailagent_simulate_message) - Not for human privacy burners — programmatic agent inboxes with allowlists
Install (pick one)
Cursor (project)
MCP in .cursor/mcp.json → @mailagent/mcp or mcp/dist/index.js. Skill auto-loads from .cursor/skills/mailagent-mcp/ (synced from this file).
Agent Skills catalog (repo root)
npx skills add Alex0nder/MailAgent --skill mailagent
OpenAI Codex
codex plugin marketplace add Alex0nder/MailAgent
codex plugin add mailagent@mailagent
Guide: https://webmailagent.com/docs/codex.html
npm MCP (any client)
export MAILAGENT_API_URL=https://api.webmailagent.com
export MAILAGENT_API_KEY=ma_…
npx -y -p @mailagent/[email protected] mailagent-mcp
Remote (no subprocess): POST https://api.webmailagent.com/mcp + Bearer token.
SDK (without MCP)
| Package | Install |
|---|---|
@mailagent/agent |
npm install @mailagent/agent |
@mailagent/qa |
npm install @mailagent/qa (Playwright) |
mailagent-agent |
pip install mailagent-agent (Python) |
Browser login (no API key in client): Auth0 OIDC on prod — auth.oidc: enabled on GET /v1/agent. Operator setup: npm run wizard:auth0. Docs: https://webmailagent.com/docs/oauth-idp.html
Prerequisites
MAILAGENT_API_KEY— console dashboard team keys, or MailAgent reponpm run issue:key:dbwhen self-hosting- MCP server
mailagentconnected (codex mcp list/ Cursor MCP refresh) - Always set
servicepreset orexpectFrom(sender allowlist)
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.
- 3d ago First seen · 257 lines · 43 tokens per session scan A 342745ffa80e
mailagent is a skill published in the GitHub repository hashgraph-online/awesome-codex-plugins (859 stars, last pushed 4d ago), licensed Apache-2.0. It adds 43 tokens to every session and 3,323 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
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
om-integration-tests
Run and create QA integration tests (Playwright TypeScript), including executing the full suite, converting optional markdown scenarios, and generating new tests from specs or feature descriptions. Defers all environment boot/reuse to the om-prepare-test-env skill and attaches to the shared descriptor it writes. Use…
cli-testing
Manually test a running Vellum assistant end-to-end purely from the CLI — no desktop app or web UI. Hatch an instance, send messages, watch the reply, and tear it down. Use when verifying assistant behavior, reproducing a bug, or smoke-testing a change without the macOS/web clients.
chrome-cdp
Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…
e2e
Run end-to-end tests via the CI workflow.