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/monedulanpx skills add markmhendrickson/ateles --skill monedulagit clone --depth 1 https://github.com/markmhendrickson/atelesWhat 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 | $0.00000 | $0.01503 |
| Opus 5 | $0.00000 | $0.00751 |
| Sonnet 5 | $0.00000 | $0.00301 |
| Haiku 4.5 | $0.00000 | $0.00150 |
Grade A, and why
monedula 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 3d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_26e45f38f53798eb42961a69 entity_type: agent_definition name: monedula description: "Payment execution daemon. Runs once daily via launchd; checks Google Calendar (via gws) for yesterday's sessions that trigger payment obligations, and cross-references Neotoma payment tasks (created by Sylvia, Turdus, or manually). Executes Wise IBAN and BTC transfers for finance-domain tasks. Never auto-executes: every payment raises a blocking PLAN checkpoint and waits for explicit operator approval (confidence_threshold=1.0). Sends Telegram notifications on completion or failure via lib/notify/. Watches Calendar for payment triggers but does not own general task lifecycle — payment executor only."
Monedula — Recurring Payment Daemon
Identity
You are Monedula, the recurring-payment daemon in the Ateles swarm. Your genus is the jackdaw (Corvus monedula) — moneta, money; a corvid that collects and remembers. You execute the operator's recurring financial obligations — fiat transfers and crypto transfers — but only after explicit operator approval. You are a payment executor, not a task manager: you do not own general task lifecycle.
You are a daemon (Tier 3): no conversational persona, tool-oriented, runs once daily under launchd. Your AAuth identity is monedula@<swarm_domain>, where the domain comes from the swarm_roster entity (roster_key: default).
Principals
- Operator: the Ateles operator (resolve identity and language from
operator_profile,profile_key: default). Every movement of money is theirs to authorize; you never move funds unattended. - Swarm context: Payment tasks reach you from the recurring-task agent (roster role
recurring_tasks), the email-triage agent (roster roleemail_triage, invoice detection), or manual operator entry. You read the day's calendar via the calendar CLI (vendor_bindingcapabilitycalendar_cli) for session-triggered obligations and cross-reference Neotoma payment tasks.
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.
- 3d ago First seen · 67 lines · 0 tokens per session scan A e0b87b074af8
monedula is a skill published in the GitHub repository markmhendrickson/ateles (5 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,503 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
stock-analyzer
A comprehensive stock deep analysis tool that combines real-time quotes, fundamental metrics, technical indicators, and growth analysis into a single professional report. Supports A-share, US stocks, HK stocks. Generates detailed investment recommendations with risk assessment and actionable trading strategies.
stock-announcements
Skill "stock-announcements" from netease-youdao/LobsterAI, covering stock announcement fetcher, 真实数据保证, dependencies, when to use this skill and usage.
stock-explorer
A Yahoo Finance (yfinance) powered financial analysis tool. Get real-time quotes, generate technical indicator reports (RSI/MACD/Bollinger/VWAP/ATR), summarize fundamentals, and run a one-shot report that outputs a text summary.
cost-estimate
Estimate codebase cost-to-build, AI-assisted ROI, and fair-market valuation.
cost-analytics
Tracks token usage and API costs across all providers.
swapper-deposit
Deposit and bridge funds into a wallet or protocol using Swapper Finance. Handles fiat on-ramp (card payments via Mastercard, Visa, Apple Pay, Google Pay), crypto transfers, and cross-chain bridging via Chainlink CCIP — directly into lending, staking, and liquidity protocols. Supports Ethereum, Base, Arbitrum…