ecl-computation

ecl-computation is a command for Claude Code from GAJETOso/financeskills. It costs 22 tokens per session (123 once invoked), scanned A, a copy of ai-anomaly-detection, MIT.

A guide for calculating expected credit loss, the amount a lender expects not to collect from loans or other credit. It covers IFRS 9, an international accounting standard, and CECL, the US current expected credit loss method.

In plain words
What is it for?
Use it to estimate loan losses, support financial reporting, or review an expected-credit-loss calculation under IFRS 9 or CECL.
Why use it?
It removes the need to calculate credit-loss figures by hand and makes assumptions and source references visible. Results still need review by a qualified professional.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the finance-skills plugin — 48 skills, 52 commands shipped together

Good fit Use it to estimate loan losses, support financial reporting, or review an expected-credit-loss calculation under IFRS 9 or CECL.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/gajetoso/financeskills/ecl-computation
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.

Clone the repo
git clone --depth 1 https://github.com/GAJETOso/financeskills

Made for: Claude Code.

Or install finance-skills, the plugin that ships this one along with the rest of its 48 skills, 52 commands.

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 ecl-computation

README.md
[![agentmods](https://agentmods.dev/badge/commands/gajetoso/financeskills/ecl-computation/github.svg)](https://agentmods.dev/commands/gajetoso/financeskills/ecl-computation)
Your own site
<a href="https://agentmods.dev/commands/gajetoso/financeskills/ecl-computation"><img src="https://agentmods.dev/badge/commands/gajetoso/financeskills/ecl-computation/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.

agentmods 80×15 button for ecl-computation

Your own site · 80×15
<a href="https://agentmods.dev/commands/gajetoso/financeskills/ecl-computation"><img src="https://agentmods.dev/badge/commands/gajetoso/financeskills/ecl-computation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 123 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 75% copy Near-identical to another mod 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 5.1 $0.00022 $0.00123
Opus 5 $0.00011 $0.00062
Sonnet 5 $0.00004 $0.00025
Haiku 4.5 $0.00002 $0.00012

Measured 9d ago against content hash 73727383241d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ecl-computation 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 9d 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.

Origin

This is a copy

75% identical to ai-anomaly-detection — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

commands/ecl-computation.md · 13 lines

What it actually says

Load and follow the skill at skills/ecl-computation/SKILL.md, including its Initial Assessment.

Input: $ARGUMENTS

Requirements:

  • Perform ALL calculations by importing functions from skills/ecl-computation/scripts/calculate.py - never mental math
  • Follow the skill's Output Format section and cite which references you used
  • State confidence and assumptions where inputs are incomplete; outputs require review by a qualified professional
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. 9d ago First seen · 13 lines · 22 tokens per session scan A 73727383241d

Subscribe to this mod's changes

ecl-computation is a command published in the GitHub repository GAJETOso/financeskills (18 stars, last pushed 7d ago), licensed MIT. It adds 22 tokens to every session and 123 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 75% identical to ai-anomaly-detection, differing in 6 lines, and is treated as a copy.