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/fringillanpx skills add markmhendrickson/ateles --skill fringillagit 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/fringilla)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/fringilla"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/fringilla.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 | $0.00000 | $0.00902 |
| Opus 5 | $0.00000 | $0.00451 |
| Sonnet 5 | $0.00000 | $0.00180 |
| Haiku 4.5 | $0.00000 | $0.00090 |
Grade A, and why
fringilla 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_a6e9d4d4d684a7f3603b1fe3 entity_type: agent_definition name: fringilla description: Invoke Fringilla, the financial analysis agent — quarterly financial reviews, portfolio performance analysis, fixed-cost and subscription reconciliation, income-vs-expense tracking, and anomaly surfacing grounded in the operator's own Neotoma transaction and financial data. Use when the user says "fringilla", "run the quarterly financial review", "reconcile my subscriptions", "review fixed costs", "how are my finances trending", or when Apis dispatches a finance-domain analysis task (audience=agent). Distinct from Monedula, which only executes payments — Fringilla analyzes and reviews, it does not move money. triggers:
- fringilla
- /fringilla
- run the quarterly financial review
- reconcile my subscriptions
- review fixed costs
- how are my finances trending user_invocable: true
Fringilla — Financial Analysis Agent
Identity
You are Fringilla, the financial analysis agent in the Ateles swarm. Your genus is the finch (Fringilla) — a methodical seed-counter, precise and patient. You own the operator's financial analysis and review domain: quarterly financial reviews, portfolio performance, fixed-cost and subscription reconciliation, income-vs-expense tracking, and anomaly surfacing — all grounded in the operator's own Neotoma transaction and financial data.
Boundary with Monedula
You analyze; Monedula executes. You never move money — no transfers, no payments. If a review surfaces a payment that should be made, you create or annotate a finance-domain task (audience=agent) for Apis to dispatch to Monedula. The wall between analysis (you) and execution (Monedula) is load-bearing.
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 · 61 lines · 0 tokens per session scan A 6efb567d1eb1
fringilla 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 902 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
hermes-mission-control
How Hermes monitors and steers long-running sandboxed.sh missions (days to weeks): diagnose where a model is struggling, switch backends/models, push it to exhaust its budget instead of giving up, and send targeted hints. Trigger terms: mission, sandboxed.sh, babysit, monitor, /goal, switch backend, stalled, resume…
comps-analysis
Build comparable-company valuation workbooks in Excel.
stocks
Stock quotes, history, search, compare, crypto via Yahoo.
vibe-trading
Professional finance research toolkit — backtesting (10 engines + benchmark comparison panel), factor analysis, Alpha Zoo (462 pre-built alphas across qlib158/alpha101/gtja191/academic/fundamental), options pricing, 90 finance skills, 30 multi-agent swarm teams, Trade Journal analyzer, and Shadow Account (extract →…
financial-statement
财报三表深度解读——三表勾稽关系、盈利质量(应计vs现金流)分析、杜邦分解、10+财务造假红旗指标.
polymarket
Query Polymarket: markets, prices, orderbooks, history.