sendmux-management
Use this skill for Sendmux account/team administration with a root API key or Management-scoped OAuth connection.
Skill by sendmux
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sendmux-sendmux-management
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, testing, security, productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/sendmux-management
What's inside
- Skill name
sendmux-management- Description
- Use this skill for Sendmux account/team administration with a root API key or Management-scoped OAuth connection. This is the go-to skill for domain lifecycle work — create a sending domain, fetch its DNS/zone-file records, verify DNS/MX — even if asked as a single quick step. Also use it for provisioning, suspending, or deleting mailboxes and mailbox API keys; configuring sending accounts/providers; creating, testing, or rotating webhooks; checking billing, spend, or balance; and pulling delivery, incoming, or metrics logs for reporting or admin purposes. This is account/team-level administration, not inbox usage: do not trigger for reading, searching, triaging, syncing, or replying to messages inside a specific mailbox (use sendmux-mailbox-agent), one-off transactional sending (sendmux-send-email), or initial setup/login (sendmux-getting-started).
- License
- Apache-2.0
- Metadata
- author: sendmux · version: 1.0
- Instructions
- 258 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Sendmux management
Use this skill for team administration with an `smx_root_` key or a REST OAuth grant with Management access.
## Boundaries
- Do not ask the user to paste an API key or one-time secret.
- Use a root API-key profile or OAuth profile with Management access and the operation's required scopes. OAuth remains limited by the authorising user's current team permissions.
- Agent self-registration does not require Management or a root key. Route a user who only wants an agent inbox to `sendmux-getting-started` and `sendmux agent:register`.
- Do not use management calls to read, triage, sync, or reply from a mailbox; route those tasks to `sendmux-mailbox-agent`.
- Treat create-key and webhook-secret responses as sensitive one-time values. Put them only in the user's chosen secret store or secure output path.
- Confirm destructive operations before deleting domains, mailboxes, mailbox keys, sending accounts, or webhooks.
- Confirm the target resource before suspend, resume, rotate-secret, or test-delivery operations.
## Surface choice
| Task | Preferred surface |
| --- | --- |
| Domains | MCP for list/create/get/zone-file/verify; CLI or SDK for update/delete/filter rules. |
| Mailboxes | MCP for list/create/get/update/suspend/resume/key create/key delete; CLI or SDK for delete and filters. |
| Sending accounts | CLI or SDK. MCP does not curate provider tools yet. |
| Webhooks | MCP for list/create/test; CLI or SDK for get/update/delete/rotate-secret/deliveries/payloads. |
| Billing and spend | MCP `management_get_spend_summary`; CLI or SDK for balance and transactions. |
| Outbound delivery logs and metrics | MCP for list/get logs and metrics; CLI or SDK also work. |
| Incoming logs | CLI or SDK. MCP does not curate incoming-log tools yet. |
For terminal work, use the `sendmux` CLI with `--json`. For application code, use `@sendmux/management` and `createManagementClient`.
SDK clients accept `accessToken` instead of `apiKey`, including a provider that resolves the current token before each request.
## Check connection and permissions
Explain the selected connection in this order:
1. Validate it with `sendmux management:get-connection --profile work --json`, replacing `work` with the selected profile. This check requires Management access but no additional read permission.
2. Interpret the response using the schema example below. `data.credential.type` identifies `api_key`, `oauth`, or `agent_token`; `data.permissions` contains effective permission names. `data.label` is a server-provided connection display label, not the local CLI profile name. Explain fields without exposing account metadata unnecessarily.
3. Match the requested operation to its advertised scopes and the authorising user's current team permissions. Use the operation-specific mappings in this skill or inspect that operation's `security` entry in the public Management OpenAPI before naming its scope. Scope names cannot be inferred from an operation's name. Login/re-consent chooses requested scopes; automatic token refresh preserves the existing grant rather than choosing extra permissions.
4. Close with the handoffs: OAuth login and token lifecycle → `sendmux-cli`; agent self-registration → `sendmux-getting-started`; mailbox read, search, sync, triage, or replies → `sendmux-mailbox-agent`. Management access does not replace those workflows.
This synthetic example shows the CLI response shape, not a verified account:
```json
{
"ok": true,
"meta": { "request_id": "EXAMPLE_REQUEST_ID" },
"data": {
"credential": { "id": "EXAMPLE_CREDENTIAL_ID", "name": "Example connection", "type": "oauth" },
"label": "Example connection",
"team": { "id": "EXAMPLE_TEAM_ID", "name": "Example team" },
"mailboxes": [{ "id": "EXAMPLE_MAILBOX_ID", "email": "agent@example.com" }],
"permissions": ["domain.read", "billing.read"]
}
}
```
## Efficient defaults
- Use small `limit` values on list endpoints and follow `pagination.next_cursor` only when more rows are needed.
- Use `Idempotency-Key` on create, suspend, resume, rotate-secret, and test mutations that accept it.
- Use `If-None-Match` for repeated detail reads that return `ETag`.
- Use `If-Match` for update or replace operations when the API exposes optimistic concurrency.
- For questions about counts or trends, use summary or metrics endpoints before log lists.
- For one email or webhook delivery, list with filters first, then fetch the selected record.
## Domains
Use domains for sending setup and hosted mailbox domains. The two domain modes are `send_only` for outbound DNS verification and `send_receive` for outbound plus MX verification. Hosted mailboxes require `send_receive`.
MCP tools:
| Action | Tool |
| --- | --- |
| List | `management_list_domains` |
| Create | `management_create_domain` |
| Inspect | `management_get_domain` |
| DNS records | `management_get_domain_zone_file` |
| Verify DNS | `management_verify_domain` |
CLI:
```bash
SENDMUX_API_KEY="$SENDMUX_ROOT_KEY" sendmux management:create-domain \
--idempotency-key "$IDEMPOTENCY_KEY" \
--body '{"domain":"example.com","mode":"send_receive"}' \
--json
SENDMUX_API_KEY="$SENDMUX_ROOT_KEY" sendmux management:get-domain-zone-file \
--path public_id=mdom_abc \
--json
SENDMUX_API_KEY="$SENDMUX_ROOT_KEY" sendmux management:verify-domain \
--path public_id=mdom_abc \
--json
```
SDK:
```ts
import {
createManagementClient,
managementCreateDomain,
managementGetDomainZoneFile,
managementVerifyDomain,
} from "@sendmux/management";
const client = createManagementClient({ apiKey: process.env.SENDMUX_API_KEY! });
await managementCreateDomain({
client,
headers: { "Idempotency-Key": process.env.IDEMPOTENCY_KEY! },
body: { domain: "example.com", mode: "send_receive" },
});
const zone = await managementGetDomainZoneFile({
client,
path: { public_id: "mdom_abc" },
});
await managementVerifyDomain({From Sendmux/skills, Apache-2.0.
More from Sendmux/skills
- 0.642score
sendmux-attachments
sendmux
Use Sendmux attachment workflows without wasting model context on base64.
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
sendmux-cli
sendmux
Use when a user wants to run the Sendmux **CLI** (the `sendmux` terminal binary) — installing it, OAuth login/logout, connection checks, agent inbox…
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
sendmux-email-for-agents
sendmux
Use when a user wants to design or plan how an AI agent gets and uses email — giving an agent its own inbox, deciding between owner-managed vs self-registered…
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
sendmux-getting-started
sendmux
Use when a user needs Sendmux setup, OAuth connection checks, agent inbox registration, owner linking, credential validation, surface selection, or a first…
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
sendmux-mailbox-agent
sendmux
Operate inside an already-existing Sendmux mailbox on behalf of an AI agent: read, search, count, sync, triage, file, delete, thread, save or edit a reply…
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
sendmux-mcp-setup
sendmux
Set up, configure, and troubleshoot Sendmux Model Context Protocol (MCP) servers for AI agent clients.
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
sendmux-send-email
sendmux
Use when a user needs advice or implementation help for sending one or many emails through Sendmux: choose the HTTP Sending API versus SMTP, design single or…
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
sendmux-token-efficient-usage
sendmux
Use when the question is about *how to call* Sendmux cheaply, not what to send: choosing batch vs.
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
agent-email-inbox
sendmux
Use when an AI agent needs read-only triage of an existing Sendmux inbox or unsent reply text from its messages.
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
email-for-ai-agents
sendmux
Use when an AI agent needs to send one outbound email through Sendmux with human approval, including a status notification or delegated agent send.
SkillAFreshness: A★ 18Claude Code +9
Signals
- Stars
- 18
- Forks
- 1
- Open issues
- 1
- Last commit (this folder)
- Sep 15, 2026 (1 month ago)
- Last release
- Oct 15, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0
- License
- Apache-2.0
- Repository
- github.com/Sendmux/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from sendmux
- 0.642score
sendmux-attachments
sendmux
Use Sendmux attachment workflows without wasting model context on base64.
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
sendmux-cli
sendmux
Use when a user wants to run the Sendmux **CLI** (the `sendmux` terminal binary) — installing it, OAuth login/logout, connection checks, agent inbox…
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
sendmux-email-for-agents
sendmux
Use when a user wants to design or plan how an AI agent gets and uses email — giving an agent its own inbox, deciding between owner-managed vs self-registered…
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
sendmux-getting-started
sendmux
Use when a user needs Sendmux setup, OAuth connection checks, agent inbox registration, owner linking, credential validation, surface selection, or a first…
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
sendmux-mailbox-agent
sendmux
Operate inside an already-existing Sendmux mailbox on behalf of an AI agent: read, search, count, sync, triage, file, delete, thread, save or edit a reply…
SkillAFreshness: A★ 18Claude Code +9 - 0.642score
sendmux-mcp-setup
sendmux
Set up, configure, and troubleshoot Sendmux Model Context Protocol (MCP) servers for AI agent clients.
SkillAFreshness: A★ 18Claude Code +9
Cite this page
sendmux-management skill. Agent Mart. https://agentmart.dev/skills/sendmux-sendmux-management (last updated 2026-10-24)