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 skills add panaversity/agentfactory-business-plugins --skill ifrs9-staginggit clone --depth 1 https://github.com/panaversity/agentfactory-business-pluginsWrote 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/panaversity/agentfactory-business-plugins/ifrs9-staging)<a href="https://agentmods.dev/skills/panaversity/agentfactory-business-plugins/ifrs9-staging"><img src="https://agentmods.dev/badge/skills/panaversity/agentfactory-business-plugins/ifrs9-staging/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.
<a href="https://agentmods.dev/skills/panaversity/agentfactory-business-plugins/ifrs9-staging"><img src="https://agentmods.dev/badge/skills/panaversity/agentfactory-business-plugins/ifrs9-staging.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00090 | $0.01872 |
| Opus 5 | $0.00045 | $0.00936 |
| Sonnet 5 | $0.00018 | $0.00374 |
| Haiku 4.5 | $0.00009 | $0.00187 |
Grade A, and why
ifrs9-staging 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 10d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
STAGING DECISION TREE — APPLY IN THIS EXACT ORDER
STEP 1 — Test for Stage 3 (Credit Impairment)
Any one of the following triggers Stage 3: [ ] 90+ days past due [ ] Formal default event (insolvency filing, legal default notice) [ ] Significant financial difficulty, no credible recovery path [ ] Forbearance / restructuring at terms bank would not otherwise offer [ ] Partial or full write-off recognised → If ANY trigger: STAGE 3 — Lifetime ECL — Interest on NET amount
STEP 2 — Test for Stage 2 (SICR)
Any one of the following triggers Stage 2: Quantitative: [ ] 30–89 days past due (rebuttable presumption — see below) [ ] Internal rating downgraded 2+ notches since origination [ ] PD at reporting date ≥ 2x PD at origination (many banks use this) [ ] Lifetime PD exceeds bank-defined absolute SICR threshold Qualitative: [ ] On watchlist / credit monitoring list [ ] Financial covenant breach (leverage, DSCR, LTV, interest cover) [ ] Loss of major customer / key contract [ ] Adverse regulatory action on borrower [ ] Industry under systemic stress (macro-driven transfer) [ ] Parent / key affiliate significant SICR → If ANY trigger: STAGE 2 — Lifetime ECL — Interest on GROSS amount
STEP 3 — Default: Stage 1
No triggers from Step 1 or Step 2 → STAGE 1 — 12-month ECL
THE 30-DAY REBUTTABLE PRESUMPTION
IFRS 9.5.5.11: 30+ DPD creates a rebuttable presumption of SICR. Can be rebutted ONLY with documented evidence of:
- Administrative processing delay (not customer fault)
- Payment in bona fide dispute with clear resolution pathway
- Payment received shortly after reporting date (documented) CANNOT be rebutted on grounds of: past payment history, prior accommodations. DOCUMENT every rebuttal. Auditors review all instances where 30+ DPD was not staged.
STAGE CURE CONDITIONS
Stage 3 to Stage 2 Cure Requirements
All of the following must be satisfied before cure to Stage 2: a) All default triggers resolved (no longer 90+ DPD, no active forbearance) b) Satisfactory probation period completed (typically 3–6 months depending on portfolio — retail tends to 3 months, corporate 6 months) c) Updated financial information reviewed and credit assessment performed d) Credit officer sign-off on cure determination (documented) e) No new adverse information during probation period (no new covenant breaches, no adverse media, no further deterioration in financial metrics) f) If forbearance was the trigger: the borrower must have made at least 3 consecutive scheduled payments under the revised terms
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.
- 10d ago First seen · 156 lines · 90 tokens per session scan A 554c6462c4c1
ifrs9-staging is a skill published in the GitHub repository panaversity/agentfactory-business-plugins (29 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 90 tokens to every session and 1,872 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.
Other skills, from other repositories
roi-estimator
Use when estimating the ROI of adopting an LLM/agent for a workflow, with structured assumptions.
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.
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.
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.
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.
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.