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 skills add AgentComputerAI/torch --skill agentmailgit clone --depth 1 https://github.com/AgentComputerAI/torchWrote 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/agentcomputerai/torch/agentmail)<a href="https://agentmods.dev/skills/agentcomputerai/torch/agentmail"><img src="https://agentmods.dev/badge/skills/agentcomputerai/torch/agentmail/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.
<a href="https://agentmods.dev/skills/agentcomputerai/torch/agentmail"><img src="https://agentmods.dev/badge/skills/agentcomputerai/torch/agentmail.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00069 | $0.01822 |
| Opus 5.5 | $0.00028 | $0.00729 |
| Sonnet 5.5 | $0.00014 | $0.00364 |
| Haiku 4.5 | $0.00007 | $0.00182 |
Grade A, and why
agentmail 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- agentmail — 92% identical, 83 lines differ
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentMail SDK
AgentMail is an API-first email platform for AI agents. Install the SDK and initialize the client.
Installation
# TypeScript/Node
npm install agentmail
# Python
pip install agentmail
Setup
import { AgentMailClient } from "agentmail";
const client = new AgentMailClient({ apiKey: "YOUR_API_KEY" });
from agentmail import AgentMail
client = AgentMail(api_key="YOUR_API_KEY")
Inboxes
Create scalable inboxes on-demand. Each inbox has a unique email address.
// Create inbox (auto-generated address)
const autoInbox = await client.inboxes.create();
// Create with custom username and domain
const customInbox = await client.inboxes.create({
username: "support",
domain: "yourdomain.com",
});
// List, get, delete
const inboxes = await client.inboxes.list();
const fetchedInbox = await client.inboxes.get({
inboxId: "[email protected]",
});
await client.inboxes.delete({ inboxId: "[email protected]" });
# Create inbox (auto-generated address)
inbox = client.inboxes.create()
# Create with custom username and domain
inbox = client.inboxes.create(username="support", domain="yourdomain.com")
# List, get, delete
inboxes = client.inboxes.list()
inbox = client.inboxes.get(inbox_id="[email protected]")
client.inboxes.delete(inbox_id="[email protected]")
Messages
Always send both text and html for best deliverability.
// Send message
await client.inboxes.messages.send({
inboxId: "[email protected]",
to: "[email protected]",
subject: "Hello",
text: "Plain text version",
html: "<p>HTML version</p>",
labels: ["outreach"],
});
// Reply to message
await client.inboxes.messages.reply({
inboxId: "[email protected]",
messageId: "msg_123",
text: "Thanks for your email!",
});
// List and get messages
const messages = await client.inboxes.messages.list({
inboxId: "[email protected]",
});
const message = await client.inboxes.messages.get({
inboxId: "[email protected]",
messageId: "msg_123",
});
// Update labels
await client.inboxes.messages.update({
inboxId: "[email protected]",
messageId: "msg_123",
addLabels: ["replied"],
removeLabels: ["unreplied"],
});
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 300 lines · 69 tokens per session scan A e1097a65e807
agentmail is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 6mo ago), licensed MIT. It adds 69 tokens to every session and 1,822 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
nodejs
Use when building or operating a plain Node.js / Express 5 backend service: project layout, async correctness, central error middleware, fail-fast config, graceful shutdown on SIGTERM. NOT DI modules/providers/guards (that is nestjs), NOT the type system or tsconfig (that is typescript), NOT REST contract design (that…
fastapi
Use when building, reviewing, testing, securing or shipping a FastAPI / async Python service — routers, Pydantic v2 schemas, dependency injection, async SQLAlchemy 2.0, OAuth2/JWT, ASGITransport tests, production wiring. NOT language-level Python or packaging (that is python), NOT engine-level SQL (that is…
gamedev-multiplayer
Use when adding multiplayer or netcode to a game — client-server vs P2P, server authority and anti-cheat, state replication vs RPCs, prediction and reconciliation, lag compensation, plus Godot 4 / Unity NGO / Unreal wiring. NOT single-player gameplay (that is godot, unity, unreal), NOT matchmaking or server hosting…
go
Use when writing, reviewing, testing, or shipping Go code and HTTP services: idioms, %w error wrapping, goroutine/context/errgroup concurrency, net/http 1.22 routing, log/slog, project layout, table-driven tests, Go hardening. NOT language-agnostic threat modeling (that is secure-coding), NOT Dockerfile/CI shipping…
csharp-dotnet
Use when writing, reviewing, testing, or shipping C# / .NET code — ASP.NET Core APIs (minimal APIs vs controllers), EF Core data access, async correctness, solution layout in .cs/.csproj/.sln. NOT a Java/Spring backend (that is spring-boot), NOT a Node/TypeScript backend (that is nestjs), NOT framework-neutral REST…
django
Use when building, reviewing, securing, testing or shipping a Django app — models, migrations, QuerySets/managers, FBV/CBV views, forms, the admin, settings split, and Django REST Framework (serializers, ModelViewSet, permissions). NOT async FastAPI/Pydantic services (that is fastapi), NOT Postgres schema/index work…