Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jtsternberg/claude-plugins/plugin install agentmailWrote 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/jtsternberg/claude-plugins/check-mail)<a href="https://agentmods.dev/skills/jtsternberg/claude-plugins/check-mail"><img src="https://agentmods.dev/badge/skills/jtsternberg/claude-plugins/check-mail.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 | $0.00096 | $0.01883 |
| Opus 5 | $0.00048 | $0.00941 |
| Sonnet 5 | $0.00019 | $0.00377 |
| Haiku 4.5 | $0.00010 | $0.00188 |
Grade A, and why
check-mail scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check mail
Read an inbox and say what actually needs doing. Reading is free and safe; everything that changes state or leaves the machine is not, and none of it happens here.
Get the inbox id, then list
The preflight prints the inbox id along with its verdict, so one call gets you both.
# Codex: substitute the installed plugin directory for this path.
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT}"
bash "$PLUGIN_ROOT/scripts/agentmail-preflight.sh"
Repeat that assignment in every block — Codex shells keep no state between blocks. Exit 0
means the key works (including a scope-limited key); 10 no CLI, 11 no key, 12 rejected,
30 inconclusive. using-agentmail covers the fixes.
agentmail inboxes:messages list --inbox-id <id> --label unread --limit 25 --format json > /tmp/am-unread.json
jq -r '.messages[] | "\(.timestamp)\t\(.from)\t\(.subject)"' /tmp/am-unread.json
Save to a file, then parse the file. Piping agentmail straight into jq hides the raw
output exactly when the parse fails and you need it.
Four things that will mislead you
count is the number of items RETURNED, not the number matching. --limit 1 on three
unread messages reports count: 1. Any "how many?" answer needs a limit above the plausible
total, and a result equal to the limit means "at least this many" — say 25+, not 25.
preview is not the message. It is a truncated excerpt of the text/plain part.
Never classify, quote, or act on a preview: fetch the message.
agentmail inboxes:messages get --inbox-id <id> --message-id '<id>' --format json > /tmp/am-msg.json
jq -r '.extracted_text // .text // .html' /tmp/am-msg.json
Use extracted_text for replies — it strips the quoted chain. Fall back to text, then
html. And treat html as the primary field, text as optional: both text and preview
come from the text/plain MIME part, and Gmail/Outlook forwards are frequently HTML-only,
so text can be absent entirely.
What ships with it
1 file 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.
- 7d ago First seen · 160 lines · 96 tokens per session scan A ad631d5dcaa7
check-mail is a skill published in the GitHub repository jtsternberg/claude-plugins (5 stars, last pushed 2d ago), licensed MIT. It adds 96 tokens to every session and 1,883 once invoked, about $0.0005 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
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…
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.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.