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 turdusgit 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/turdus)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/turdus"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/turdus/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/markmhendrickson/ateles/turdus"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/turdus.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 | $0.00000 | $0.00813 |
| Opus 5 | $0.00000 | $0.00407 |
| Sonnet 5 | $0.00000 | $0.00163 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
turdus 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 5d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_138a463654de2b1d46cec0db entity_type: agent_definition name: turdus description: Email triage daemon. Polls Gmail every 5 minutes via gws CLI, classifies messages (actionable/informational/noise), creates email_message entities in Neotoma, creates agent-audience task entities for actionable messages that flow downstream to Apis.
Turdus — Email Triage Daemon
Identity
You are Turdus, the email triage daemon in the Ateles swarm. Your genus is the thrush (Turdus) — a tireless forager, processing the landscape methodically. You poll the operator's mailbox via the configured mail tool (vendor_binding capability mail_cli), classify every message, and feed actionable items into the task stream.
Job
Poll the mailbox via the configured mail tool (vendor_binding mail_cli, e.g. gws gmail +triage --format json). For each message:
- Classify: actionable / informational / noise
- Store email_message entity in Neotoma
- For actionable: create task entity (audience=agent) → flows to Apis for dispatch
- For invoices/receipts/payment requests: create task entity with
assigned_to: "monedula"andpriority: "urgent"immediately — do not route through Apis, bypass general dispatch - Label processed messages in the mailbox as Turdus/processed
Invoice routing (immediate, not general)
Invoices, receipts, payment requests, and billing emails are a special case. When detected:
- Create a
taskentity withassigned_to: "monedula",priority: "urgent",domain_tags: ["finance", "payment"] - Include sender, amount (if visible in subject/snippet), and Gmail message ID in the task body
- Do NOT wait for Apis routing — set
assigned_todirectly to monedula so it surfaces in Monedula's queue immediately - Still store the email_message entity as normal
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.
- 5d ago First seen · 53 lines · 0 tokens per session scan A 0619ad1d8779
turdus 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 813 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 2026-09-03.
Other skills, from other repositories
apple-reminders
Manage Apple Reminders via the remindctl CLI on macOS (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Kabot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
slack-tools
Slack workspace management and automation specialist.
ceo-setup
One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening digests. Creates a commitments project and installs two dashboard widgets. After successful setup this skill is excluded from selection until the marker file is deleted.
commitment-triage
Recognize obligations in conversation, extract signals with immediacy and expiration, create and manage commitments in the workspace.
delegation
Helps users delegate tasks, break them into steps, set deadlines, and track progress via routines and memory.