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 review-all-mailgit 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/review-all-mail)<a href="https://agentmods.dev/skills/srogerf/personal-mail-mcp/review-all-mail"><img src="https://agentmods.dev/badge/skills/srogerf/personal-mail-mcp/review-all-mail/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/review-all-mail"><img src="https://agentmods.dev/badge/skills/srogerf/personal-mail-mcp/review-all-mail.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 | $0.00610 |
| Opus 5.5 | $0.00031 | $0.00244 |
| Sonnet 5.5 | $0.00015 | $0.00122 |
| Haiku 4.5 | $0.00008 | $0.00061 |
Grade A, and why
review-all-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 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review All Mail
Overview
Use this skill to orchestrate three focused skills into one report-driven workflow:
email-appointment-harvest: check recent mail for calendar items.inbox-triage: triage Inbox archive candidates.missed-mail-review: check unread messages outside the Inbox for missed attention items.
Default Scope
- Accounts: all configured accounts unless the user narrows scope.
- Mail scan window: last seven days for calendar harvesting unless the user specifies otherwise.
- Inbox triage depth: 100-250 messages per account.
- Missed-mail depth: 30-100 unread non-Inbox messages per account.
- Calendar target: the configured calendar-owning Exchange account unless specified otherwise.
Workflow
- List or infer configured accounts and the calendar account.
- Use
email-appointment-harvestbehavior first. Do not archive appointment source emails until needed calendar entries exist or the user says they are safe to archive. - Use
inbox-triagebehavior next. Runmail_archive_plan, summarize grouped Inbox archive candidates, and reviewfilter_recommendations. - If the user asks to apply the Inbox archive plan, call
archive_messagesby account with exact ids from the plan. - Use
missed-mail-reviewbehavior last. Runmissed_mailand summarize unread non-Inbox attention candidates by account, folder, and reason. - Recommend filters for repeated noise patterns and unsubscribes for sources the user does not follow.
- Produce the final report.
Report Format
Keep the report concise:
Calendar
- Proposed: <count>; Created/updated: <count>; Needs approval: <summary>
Inbox Triage
- Archived/moved: <count by account>
- Not moved: <notable review/keep items>
Missed Mail
- Attention candidates outside Inbox: <count by account>
- Notable items: <subject/source/folder>
Filter / Unsubscribe Recommendations
- Filter: <sender/pattern> -> <suggested action and accounts>
- Unsubscribe: <sender> -> <reason>
When messages are moved, include exact subjects and counts. Avoid long email body excerpts.
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.
- 2mo ago First seen · 62 lines · 77 tokens per session scan A 74e524a81402
review-all-mail 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 610 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.