fringilla

fringilla is a skill for Claude Code, Codex from markmhendrickson/ateles. It costs 0 tokens per session (902 once invoked), scanned A, original, MIT.

A financial-analysis agent definition named Fringilla that reviews the user's own transaction and financial data. It covers recurring financial reviews, portfolio performance, fixed costs, subscriptions, income versus expenses, and unusual activity.

In plain words
What is it for?
Use it for quarterly financial reviews, portfolio performance analysis, subscription reconciliation, fixed-cost reviews, income-and-expense tracking, and finding anomalies in personal financial data.
Why use it?
It separates financial analysis from payment execution: Fringilla examines and explains data but does not move money. This helps keep review work distinct from the agent that handles payments.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/markmhendrickson/ateles/fringilla
Any agent
npx skills add markmhendrickson/ateles --skill fringilla
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/ateles

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for fringilla

README.md
[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/fringilla.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/fringilla)
Your own site
<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>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 902 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash 6efb567d1eb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/skills/fringilla/SKILL.md · 61 lines

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.

Read the full file on GitHub · 61 lines

Changes

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.

  1. 3d ago First seen · 61 lines · 0 tokens per session scan A 6efb567d1eb1

Subscribe to this mod's changes

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.