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 Thestral12/postfleet-mcp --skill postfleetgit clone --depth 1 https://github.com/Thestral12/postfleet-mcpWrote 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/thestral12/postfleet-mcp/postfleet)<a href="https://agentmods.dev/skills/thestral12/postfleet-mcp/postfleet"><img src="https://agentmods.dev/badge/skills/thestral12/postfleet-mcp/postfleet/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/thestral12/postfleet-mcp/postfleet"><img src="https://agentmods.dev/badge/skills/thestral12/postfleet-mcp/postfleet.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 | $0.00076 | $0.00941 |
| Opus 5 | $0.00038 | $0.00470 |
| Sonnet 5 | $0.00015 | $0.00188 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
postfleet 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 9d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Postfleet — email for agents
Postfleet gives this agent a real mailbox. Mail sent to it arrives in an inbox the agent can list, read, and wait on; mail the agent sends comes from its own address.
Setup
Set POSTFLEET_API_KEY to a pf_ key from https://postfleet.ai before starting the
gateway. The plugin's MCP server reads it from the environment; without it every tool
call fails with an auth error.
Tools appear as postfleet__<tool> (for example postfleet__list_mailboxes).
The one rule: start with list_mailboxes
Every mailbox-scoped tool needs a mailbox_id, and list_mailboxes is where one comes
from. Call it first. Only call create_mailbox when the list is empty or the task
genuinely needs a second, separate address — a key bound to a single mailbox returns
just that one, so the list is also the answer to "what am I allowed to use?".
Sending and replying
send_email— needsmailbox_id,to,subject,text, and aclient_idyou generate. Theclient_idis an idempotency key: reuse the same value if you retry a send, and never reuse it for a different message.reply_email— replies in-thread. Takesreply_to_message_idfromlist_inboxorread_emailrather than a fresh subject line. Prefer it oversend_emailwhenever you are answering something; it keeps the thread intact for the human on the far end.
Either call can come back as { draft_id, status: 'pending_approval' } instead of a
sent message. That is not an error — the mailbox requires human approval, and the
message is now a draft. Report that to the user rather than retrying the send.
Reading and waiting
list_inbox— recent messages, newest first.read_email— the full body of onemessage_id.wait_for_email— blocks until a matching message arrives. This is the tool for "sign up, then confirm the address": send the signup, then wait, rather than pollinglist_inboxin a loop.
Drafts
create_draft, list_drafts, get_draft, update_draft, send_draft, delete_draft.
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.
- 9d ago First seen · 88 lines · 76 tokens per session scan A 8d28e18d0b07
postfleet is a skill published in the GitHub repository Thestral12/postfleet-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 76 tokens to every session and 941 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 2026-09-04.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.