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 agentmods add skills/markmhendrickson/ateles/email-triagenpx skills add markmhendrickson/ateles --skill email-triagegit clone --depth 1 https://github.com/markmhendrickson/atelesWrote 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/markmhendrickson/ateles/email-triage)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/email-triage"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/email-triage.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 | $0.00048 | $0.03785 |
| Opus 5 | $0.00024 | $0.01893 |
| Sonnet 5 | $0.00010 | $0.00757 |
| Haiku 4.5 | $0.00005 | $0.00379 |
Grade A, and why
email-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 6d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage Email
Full inbox triage: read all emails, categorize them, store every email as an entity in Neotoma, draft replies for actionable emails, confirm with the user, send approved replies, and archive no-action emails. Supports snoozing: snoozed emails are starred, archived, and stored in Neotoma with a snoozed_until date; they resurface automatically on the next triage run when the date is due.
Prerequisites
gwsCLI must be available (which gws). This is the required Gmail interface — do NOT use the Gmail MCP server.- Neotoma prod MCP must be connected (
mcp__mcpsrv_neotoma__*). Verify withget_session_identity.
Phase 0 — Check for snoozed emails due today
Before pulling the inbox, find email entities whose CURRENT snapshot still carries a live snoozed_until date on or before today. Query server-side on the snapshot field, not by lexical search:
retrieve_entities(entity_type=\"email\", snapshot_filters={ \"snoozed_until\": { \"op\": \"lte\", \"value\": \"<today YYYY-MM-DD>\" } })
snapshot_filters matches only entities whose computed snapshot currently contains a non-null snoozed_until ≤ today, so a cleared snooze (value set back to null/absent) is excluded at the source.
Never surface a cleared snooze. Do NOT use search=\"snoozed_until\" — lexical search matches any email whose historical observations ever mentioned snoozing, including ones already cleared, and re-surfaces them every run. If for any reason you fall back to a broader query, drop every result whose current snapshot snoozed_until is null, absent, or in the future BEFORE doing anything with it — a cleared or not-yet-due snooze is invisible to triage and is never mentioned to the user, not even to note that it was skipped.
For each genuine match (live snapshot snoozed_until ≤ today), fetch the Gmail message by its message_id field. Include these messages in the triage, clearly labeled "🔔 Snoozed (due today/overdue)", and treat them as actionable. After the user acts on them, clear the snoozed_until by re-storing the entity with snoozed_until: null.
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.
- 6d ago First seen · 148 lines · 48 tokens per session scan A dbcb0d47494f
email-triage is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 3,785 once invoked, about $0.0002 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
life-automation-audit
Use this as an on-demand long prompt. Do not paste it into SOUL.md / PRINCIPLES.md / AGENTS.md. When the user asks to audit their life for automation opportunities, load and follow this prompt.
discord
Control Discord via the discord tool: manage messages, reactions, polls, channels, and bot presence.
slack
Use when you need to control Slack from Kabot via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.
bluebubbles
Use when you need to send or manage iMessages via BlueBubbles (recommended iMessage integration). Calls go through the generic message tool with channel="bluebubbles".
notion
Notion API for creating and managing pages, databases, and blocks.
himalaya
CLI to manage emails via IMAP/SMTP. Use himalaya to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).