ifrs9-ecl

ifrs9-ecl is a skill for Claude Code from panaversity/agentfactory-business-plugins. It costs 92 tokens per session (1,927 once invoked), scanned A, original, Apache-2.0.

A guide to IFRS 9 expected credit loss, the accounting estimate of future losses on loans and other credit assets. It explains when to use 12-month or lifetime loss estimates and how probability, future economic conditions, and cash-flow timing affect the estimate.

In plain words
What is it for?
Use it when assessing IFRS 9 impairment stages, calculating expected credit loss with PD, LGD, and EAD, weighting economic scenarios, handling provisions, or preparing related IFRS 7 disclosures. It does not cover US GAAP CECL.
Why use it?
It helps avoid accounting errors such as treating losses as incurred only after evidence appears, using the wrong loss horizon, or calculating interest on the wrong carrying amount.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the banking plugin — 17 skills, 4 commands shipped together

Good fit Use it when assessing IFRS 9 impairment stages, calculating expected credit loss with PD, LGD, and EAD, weighting economic scenarios, handling provisions, or preparing related IFRS 7 disclosures. It does not cover US GAAP CECL.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/panaversity/agentfactory-business-plugins/ifrs9-ecl
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.

Any agent
npx skills add panaversity/agentfactory-business-plugins --skill ifrs9-ecl
Clone the repo
git clone --depth 1 https://github.com/panaversity/agentfactory-business-plugins

Made for: Claude Code.

Or install banking, the plugin that ships this one along with the rest of its 17 skills, 4 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 ifrs9-ecl

README.md
[![agentmods](https://agentmods.dev/badge/skills/panaversity/agentfactory-business-plugins/ifrs9-ecl.svg)](https://agentmods.dev/skills/panaversity/agentfactory-business-plugins/ifrs9-ecl)
Your own site
<a href="https://agentmods.dev/skills/panaversity/agentfactory-business-plugins/ifrs9-ecl"><img src="https://agentmods.dev/badge/skills/panaversity/agentfactory-business-plugins/ifrs9-ecl.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,927 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 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 5.1 $0.00092 $0.01927
Opus 5 $0.00046 $0.00963
Sonnet 5 $0.00018 $0.00385
Haiku 4.5 $0.00009 $0.00193

Measured 8d ago against content hash c950112b6e45, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ifrs9-ecl 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 8d 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.

banking/skills/ifrs9-ecl/SKILL.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CORE PRINCIPLE

ECL is FORWARD-LOOKING and PROBABILITY-WEIGHTED. It is NOT the incurred loss. It is the probability-weighted expectation of credit losses given ALL reasonable and supportable information, including future economic conditions. Never wait for objective evidence of impairment to recognise a loss.

STAGE SUMMARY

Stage Trigger ECL Horizon Interest Income
Stage 1 No SICR since origination 12-month ECL On GROSS carrying amount
Stage 2 SICR since origination — see ifrs9-staging.md Lifetime ECL On GROSS carrying amount
Stage 3 Credit impairment occurred Lifetime ECL On NET carrying amount (gross - ECL)

CRITICAL: Stage 3 interest is on the NET amount. Recognising Stage 3 interest on the gross amount is a material accounting error.

ECL FORMULAS

12-Month ECL (Stage 1): ECL_12 = PD_12 x LGD x EAD

Lifetime ECL (Stage 2 and 3): ECL_life = Sum_t [ PD_marginal_t x LGD_t x EAD_t x DF_t ] where t = each future period until maturity DF_t = discount factor at the asset's effective interest rate

Scenario-Weighted ECL (REQUIRED): ECL = Sum_s ( Weight_s x ECL_scenario_s ) Weights must sum to 1.0 and reflect management's genuine scenario probability assessment

DISCOUNT FACTOR TREATMENT

The discount factor (DF_t) is calculated using the asset's effective interest rate (EIR). For floating-rate instruments: use current EIR at the reporting date. For fixed-rate instruments: use the EIR at initial recognition.

DF_t = 1 / (1 + EIR)^t

Discounting matters because:

  • Lifetime ECL for long-dated assets (e.g., 25-year mortgages) extends decades
  • Without discounting, future losses are materially overstated in present-value terms
  • The discount effect is largest for Stage 2 facilities with long remaining maturity

Read the full file on GitHub · 180 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. 8d ago First seen · 180 lines · 92 tokens per session scan A c950112b6e45

Subscribe to this mod's changes

ifrs9-ecl is a skill published in the GitHub repository panaversity/agentfactory-business-plugins (29 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,927 once invoked, about $0.0005 per session on Opus 5. 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 2026-08-30.

Related

Other skills, from other repositories

roi-estimator

Use when estimating the ROI of adopting an LLM/agent for a workflow, with structured assumptions.

staruhub/CrewClaw · 24 tokens

mcp_paypal

Operate PayPal through its official remote MCP in the configured sandbox or live environment. Use when the user asks to create/send invoices, manage orders and payments, issue refunds, handle disputes, manage products or subscriptions, track shipments, or read transactions.

manor-os/manor-ai · 54 tokens

mcp_stripe

Operate Stripe through the official remote Stripe MCP (mcp.stripe.com). Use when the user asks to read or update Stripe API resources, issue refunds, plan an integration, run reports, inspect the connected account, or search Stripe documentation.

manor-os/manor-ai · 53 tokens

mcp_quickbooks

Operate the user's QuickBooks Online company through the QuickBooks MCP. Use when the user asks to look up or create customers and invoices, send or void an invoice, review payments/bills/accounts/vendors, or run a financial report.

manor-os/manor-ai · 52 tokens

mcp_square

Operate the user's Square account through the Square MCP. Use when the user asks to look up locations, catalog items, orders, or customers, create catalog items or customers, or read/adjust inventory counts on Square.

manor-os/manor-ai · 47 tokens

finance-ledger

Read, query, and record validated income, expense, invoice, bill, payment, refund, transfer, adjustment, and journal-entry facts in the active Workspace Finance Ledger.

manor-os/manor-ai · 38 tokens