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/customware-ai/skills/customware-emailnpx skills add customware-ai/skills --skill customware-emailgit clone --depth 1 https://github.com/customware-ai/skillsWrote 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/customware-ai/skills/customware-email)<a href="https://agentmods.dev/skills/customware-ai/skills/customware-email"><img src="https://agentmods.dev/badge/skills/customware-ai/skills/customware-email.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 5.1 | $0.00066 | $0.01861 |
| Opus 5 | $0.00033 | $0.00931 |
| Sonnet 5 | $0.00013 | $0.00372 |
| Haiku 4.5 | $0.00007 | $0.00186 |
Grade A, and why
customware-email 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 6d 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Customer Email
Implement one coherent Customware email capability for a Customware-generated app. The capability receives customer replies through the provisioned Postmark inbound webhook and sends customer-facing messages through the same development Postmark server's HTTPS API.
The task provides the project-specific addresses. The two managed server ENV values provide the credentials. This skill provides the implementation method, durable behavior, and verification contract.
Build toward the existing app. Reuse its Hono routes, Drizzle schema, SQLite database, logging, error, and
Resultpatterns. A small, native integration is easier to reason about and safer than a second email framework.
Read first
Read these references before editing source files:
- references/common-architecture.md — task inputs, platform boundaries, credentials, stack, and shared integration shape.
- references/inbound.md — the fixed webhook, authentication, durable receipt, deduplication, and recovery contract.
- references/outbound.md — direct Postmark API sending, message shape, sender/reply routing, and failure handling.
- references/common-quality.md — validation, safe logging, migration, tests, and final verification.
Read the inbound and outbound references even when the task initially sounds one-sided. Replies make the two directions one feature: inbound mail must be able to reach the app, and outbound mail must route replies back to the same virtual address.
<read_order>
Before implementation, also read the target repository's AGENTS.md, the complete Builder task, relevant project docs, and the existing database/route/service contracts. Treat the target repository as authoritative when a framework detail differs from an example here.
</read_order>
Fixed platform contract
| Concern | Required decision |
|---|---|
| Postmark server | Use the one development server already provisioned for this project. The app does not create, delete, or configure it. |
| Inbound route | POST /api/email/inbound |
| Inbound authentication | HTTP Basic Auth, username customware, password from POSTMARK_INBOUND_WEBHOOK_SECRET |
| Server credentials | Read POSTMARK_INBOUND_WEBHOOK_SECRET and POSTMARK_SERVER_TOKEN only on the server. |
| Inbound address | Use the exact virtual address supplied in the task. Do not create an ENV for it. |
| Outbound sender | Use the exact task-provided sender, currently [email protected]. Do not create an ENV for it. |
| Outbound stream | Postmark's existing Default Transactional stream (outbound). |
| Transport | Direct HTTPS requests to Postmark's Email API from server code. |
| SMTP | Do not enable or use SMTP. |
| Customware gateway | Do not add a Customware send endpoint, proxy, or email gateway. |
| Production | Implement the development capability described by the task. Do not add production-server, publish, or environment-branching behavior. |
What ships with it
5 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.
- 6d ago First seen · 118 lines · 66 tokens per session scan A ed169fdc4d8a
customware-email is a skill published in the GitHub repository customware-ai/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 1,861 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 2026-08-31.
Other skills, from other repositories
omni-mcp
Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.