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 srogerf/personal-mail-mcp --skill inbox-triagegit clone --depth 1 https://github.com/srogerf/personal-mail-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/srogerf/personal-mail-mcp/inbox-triage)<a href="https://agentmods.dev/skills/srogerf/personal-mail-mcp/inbox-triage"><img src="https://agentmods.dev/badge/skills/srogerf/personal-mail-mcp/inbox-triage/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/srogerf/personal-mail-mcp/inbox-triage"><img src="https://agentmods.dev/badge/skills/srogerf/personal-mail-mcp/inbox-triage.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 | $0.00077 | $0.00535 |
| Opus 5.5 | $0.00031 | $0.00214 |
| Sonnet 5.5 | $0.00015 | $0.00107 |
| Haiku 4.5 | $0.00008 | $0.00053 |
Grade A, and why
inbox-triage 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 2mo 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Inbox Triage
Workflow
Use this skill only for messages currently in the Inbox. Use missed-mail-review for unread messages outside the Inbox.
Prefer mail_archive_plan for routine Inbox cleanup because it is read-only and returns exact message ids grouped by account and archive reason. Use mail_audit when the user wants the full keep/archive/review/flag breakdown, mail_inbox for account-specific inspection, and archive_messages only with exact message ids from the plan or a direct user instruction.
Start read-only:
- Identify accounts to inspect. If the user says "all inboxes," use all configured mail accounts.
- Run
mail_archive_planwith enough depth for the request, usually 100-250 Inbox messages per account. - Show the grouped archive plan with account id, reason, message id, subject, sender, and received date.
- If the user asks to apply the plan, call
archive_messageswith the exact ids from the plan. - Summarize what changed and what remains for review.
Safety
Never delete mail. Archive means remove from Inbox or move to Archive while preserving the message. Do not move messages from a new, ambiguous, financial, medical, tax-related, legal, personal, appointment-related, or potentially actionable pattern unless the dry-run plan makes the action clear or the user directs the move.
Keep future appointment, reservation, ticket, bill, payment, tax, security, healthcare, HOA, shipment, order, refund, and account-access messages unless a stronger user rule says otherwise. If a mail item looks like a future appointment, mention it and do not archive it until any needed calendar entry exists and the user approves.
Rules
For detailed retention and classification rules, read references/rules.md when running an Inbox cleanup or when explaining why a message belongs in a bucket.
If a user changes a rule during triage, apply it to the current batch and consider updating the MCP server's deterministic rules if the pattern should persist across future audits.
What ships with it
2 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.
- 2mo ago First seen · 37 lines · 77 tokens per session scan A 39c76eb0d63a
inbox-triage is a skill published in the GitHub repository srogerf/personal-mail-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 77 tokens to every session and 535 once invoked, about $0.0003 per session on Opus 5.5. 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…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
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.