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 anrawool/mailrith-agent-platform --skill mailrith-email-marketinggit clone --depth 1 https://github.com/anrawool/mailrith-agent-platformWrote 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/anrawool/mailrith-agent-platform/mailrith-email-marketing)<a href="https://agentmods.dev/skills/anrawool/mailrith-agent-platform/mailrith-email-marketing"><img src="https://agentmods.dev/badge/skills/anrawool/mailrith-agent-platform/mailrith-email-marketing/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/anrawool/mailrith-agent-platform/mailrith-email-marketing"><img src="https://agentmods.dev/badge/skills/anrawool/mailrith-agent-platform/mailrith-email-marketing.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 | $0.00075 | $0.00833 |
| Opus 5 | $0.00037 | $0.00417 |
| Sonnet 5 | $0.00015 | $0.00167 |
| Haiku 4.5 | $0.00007 | $0.00083 |
Grade A, and why
mailrith-email-marketing 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 10d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mailrith Email Marketing
Use Mailrith's discovery contract before choosing tools and request only the permissions the task needs.
Start Every Workflow
- Read the connected workspace and capabilities before assuming an action is available.
- Confirm the selected workspace, credential identity, and granted scopes.
- Convert the user's request into the smallest sequence of Mailrith operations.
- Prefer reads and drafts first. Run the documented preflight check before sending.
- Execute only operations allowed by the credential's scopes and the user's requested task.
- Return the request ID, resource IDs, current status, and a clear next step.
Read references/workflows.md for exact Subscriber, Broadcast, Sequence, execution, monitoring, and diagnostic recipes. Read references/connections.md when connecting an agent client. Read references/safety.md before retrying a mutation or handling an uncertain outcome.
Choose The Interface
- Prefer the hosted MCP server when the client supports Streamable HTTP and OAuth.
- Use the standard
https://api.mailrith.com/mcpURL. Full Email Marketing Access is the default for a general-purpose agent. Choose a focused Work Profile only when the connection has a deliberately narrower job. - Prefer the CLI for shell-based agents, CI, or deterministic JSON pipelines.
- Prefer the TypeScript or Python SDK when building an application.
- Use raw HTTP only when the runtime cannot use an official client.
For an MCP connection, call discovery_get_capabilities first. If the client asks the user to connect, finish OAuth, choose the appropriate Work Profile, and call it again to confirm the selected workspace and granted permissions. Run mailrith capabilities --json before using the CLI. Then choose the focused tool whose name and schema match the requested action. Keep draft editing, preflight, testing, activation, scheduling, and sending as separate calls. In the CLI, use mailrith operations search "<task>" --json and mailrith operations describe <operation-id> --json before calling an unfamiliar operation. CLI search and schema inspection work before authentication and do not make a network request. If several operations could produce different effects, narrow the request or ask the user which effect they intend before executing anything. Do not hard-code undocumented paths, permissions, operation IDs, enum values, or retry rules.
What ships with it
4 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.
- 10d ago First seen · 48 lines · 75 tokens per session scan A 8d89126342c8
mailrith-email-marketing is a skill published in the GitHub repository anrawool/mailrith-agent-platform (0 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 833 once invoked, about $0.0004 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
data-visualization
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
deepagents-thread-inspector
Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata, list recent local threads, or parse…
query-writing
Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables.