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 fanfan-de/anybox --skill gmail-inbox-triagegit clone --depth 1 https://github.com/fanfan-de/anyboxWrote 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/fanfan-de/anybox/gmail-inbox-triage)<a href="https://agentmods.dev/skills/fanfan-de/anybox/gmail-inbox-triage"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/gmail-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/fanfan-de/anybox/gmail-inbox-triage"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/gmail-inbox-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00063 | $0.00461 |
| Opus 5 | $0.00032 | $0.00230 |
| Sonnet 5 | $0.00013 | $0.00092 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
gmail-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 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.
What it actually says
Gmail Inbox Triage
Overview
Use this skill for direct inbox-triage requests. Build on the core Gmail skill at ../gmail/SKILL.md, especially its search and thread-reading guidance.
Workflow
- Default to
INBOXand a clear timeframe unless the user asks for a broader audit. - Use
search_emailsto build a shortlist before reading bodies. - Exclude obvious noise early if newsletters, calendar churn, or automated alerts dominate the first pass.
- Use
batch_read_emailonly when snippets are not enough to classify urgency or reply-needed status. - Escalate to
read_email_threadwhen a message appears to be part of an active conversation and the surrounding thread may change the classification. Be careful because low-signal notifications can turn into long threads;read_email_threadexposestotal_messages, which helps detect that. - Return the result in explicit Inbox Zero-style buckets such as
Urgent,Needs reply soon,Waiting, andFYI.
Bucket Heuristics
Urgent: direct asks with time pressure, blocking messages, decision requests with deadlines, or operational mail that can break if ignored.Needs reply soon: direct asks without same-day urgency, active conversations where the user is the next responder, or follow-ups that will go stale if ignored.Waiting: threads where the user already replied or the current blocker belongs to someone else.FYI: announcements, newsletters, calendar churn, and transactional mail that does not require action.
Output
- Include sender, subject, why each item is in its bucket, and the likely next action.
- State timeframe, search scope, and confidence.
- Treat reply-needed as an inference, not a guaranteed state.
- Avoid claiming the inbox is fully triaged if you only checked a narrow slice.
What ships with it
3 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.
- 9d ago First seen · 34 lines · 63 tokens per session scan A 1ce1ef20bbe9
gmail-inbox-triage is a skill published in the GitHub repository fanfan-de/anybox (57 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 461 once invoked, about $0.0003 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 2026-09-03.
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…
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.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.