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 markmhendrickson/ateles --skill email-triage-autogit 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-auto)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/email-triage-auto"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/email-triage-auto.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 | $0.00000 | $0.02219 |
| Opus 5 | $0.00000 | $0.01110 |
| Sonnet 5 | $0.00000 | $0.00444 |
| Haiku 4.5 | $0.00000 | $0.00222 |
Grade A, and why
email-triage-auto 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 8d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
name: email-triage-auto description: "Autonomous, no-HITL hourly email sweep run by the Turdus daemon. Stores EVERY email from the last 24 hours in Neotoma regardless of inbox membership (thorough memorization), prepares Gmail drafts for actionable messages using existing Neotoma context, creates tasks, and pushes two Telegram digests to the operator (action + informational). NEVER sends replies and NEVER archives — drafts stay inert until the operator sends them. For interactive human-driven triage use the email-triage skill instead. Trigger: Turdus hourly schedule, or operator request for an autonomous/background email sweep." user_invocable: false triggers:
- autonomous email sweep
- background email triage
- turdus hourly email
- auto triage
- email sweep entity_id: ent_b5f44a176d9ee06f5a45609d
Autonomous Email Triage (Turdus)
A no-human-in-the-loop email sweep designed to run unattended on an hourly cadence inside the Turdus daemon (T3, aauth_sub turdus@ateles-swarm). It is the autonomous counterpart to the interactive email-triage skill. They share storage and classification conventions but differ in control flow: this skill NEVER pauses for confirmation and NEVER takes an irreversible outward action.
Hard boundaries (non-negotiable)
- NEVER send an email. Only ever create Gmail drafts (create_draft). A draft is inert until the operator opens Gmail and sends it. No auto-send path, ever, regardless of how routine the reply looks.
- NEVER archive or modify labels beyond Turdus's own processed-label bookkeeping. Archiving stays a human action (interactive email-triage skill or operator).
- NEVER delete anything.
- These boundaries hold even if a caller passes flags asking to relax them. Outbound sending/archiving would be a separate, explicitly-approved skill — not this one.
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.
- 8d ago First seen · 79 lines · 0 tokens per session scan A ae9bfaf3609e
email-triage-auto is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,219 tokens. 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).