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 igptai/skills --skill invoice-reconciliationgit clone --depth 1 https://github.com/igptai/skillsWrote 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/igptai/skills/invoice-reconciliation)<a href="https://agentmods.dev/skills/igptai/skills/invoice-reconciliation"><img src="https://agentmods.dev/badge/skills/igptai/skills/invoice-reconciliation/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/igptai/skills/invoice-reconciliation"><img src="https://agentmods.dev/badge/skills/igptai/skills/invoice-reconciliation.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 | $0.00087 | $0.01311 |
| Opus 5 | $0.00044 | $0.00656 |
| Sonnet 5 | $0.00017 | $0.00262 |
| Haiku 4.5 | $0.00009 | $0.00131 |
Grade A, and why
invoice-reconciliation 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invoice Reconciliation
Prerequisites
This skill needs the iGPT MCP at https://mcp.igpt.ai/.
If the MCP tools aren't available or return an auth error, tell the
user to install the iGPT plugin (/plugin marketplace add igptai/skills)
or add https://mcp.igpt.ai/ as a connector, then complete OAuth and say
"ready". Retry once after they confirm. Never invent tokens or OAuth URLs.
For deeper troubleshooting: https://raw.githubusercontent.com/igptai/skills/main/shared/mcp-guard.md
What This Skill Does
Finds all invoices received via email, extracts the amount, currency, sender, and date for each, converts every amount to the user's local currency, and returns a clean structured schema the user can send directly to their accountant or import into accounting software.
Workflow
-
Before calling any tool, collect these values from the user. Offer the defaults and let the user override them; do not invent values they did not give.
- [time_range] — what window of email to scan. The user may give this in any form ("the current month", "last 30 days", "May 2024"). Default: the current calendar month. Keep the user's natural phrasing for use in the ask input; convert to ISO dates separately for the search call.
- [local_currency] — the currency to convert all amounts into (e.g. USD, EUR, ILS). No default — must come from the user.
-
Call search with:
- query: invoice receipt billing payment due amount
- date_from: ISO start date derived from [time_range]
- date_to: ISO end date derived from [time_range] (or today if open-ended)
-
Call ask with:
- input: Find all invoices and billing emails received in [time_range]. For each invoice extract: the sender company or name, the invoice number if present, the invoice date, the amount due, and the currency. Then convert each amount to [local_currency] using current exchange rates. Return every invoice as a structured record.
- output_format: { "strict": true, "schema": { "type": "object", "description": "Invoice reconciliation report for a specific time period", "additionalProperties": false, "properties": { "period_from": { "type": "string", "description": "ISO8601 start date of the reconciliation period" }, "period_to": { "type": "string", "description": "ISO8601 end date of the reconciliation period" }, "local_currency": { "type": "string", "description": "The currency all amounts have been converted to (e.g. USD, EUR, ILS)" }, "invoices": { "type": "array", "description": "List of every invoice found in email during the period", "items": { "type": "object", "description": "A single invoice extracted from email", "additionalProperties": false, "properties": { "sender": { "type": "string", "description": "Company or person who sent the invoice" }, "invoice_number": { "type": "string", "description": "Invoice number or reference, empty string if not found" }, "invoice_date": { "type": "string", "description": "ISO8601 date of the invoice" }, "original_amount": { "type": "number", "description": "The invoice amount in its original currency" }, "original_currency": { "type": "string", "description": "The currency code of the original invoice amount (e.g. USD, EUR, GBP)" }, "converted_amount": { "type": "number", "description": "The invoice amount converted to the user's local currency" }, "converted_currency": { "type": "string", "description": "The local currency code the amount was converted to" }, "due_date": { "type": "string", "description": "ISO8601 payment due date, empty string if not found" }, "status": { "type": "string", "description": "Payment status based on email evidence", "enum": ["paid", "unpaid", "unknown"] } }, "required": [ "sender", "invoice_number", "invoice_date", "original_amount", "original_currency", "converted_amount", "converted_currency", "due_date", "status" ] } }, "total_converted": { "type": "number", "description": "Sum of all invoice amounts converted to local currency" }, "total_unpaid_converted": { "type": "number", "description": "Sum of all unpaid invoice amounts converted to local currency" }, "summary": { "type": "string", "description": "One or two sentence summary of total invoices found, total amount, and any unpaid items" } }, "required": [ "period_from", "period_to", "local_currency", "invoices", "total_converted", "total_unpaid_converted", "summary" ] } }
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 · 149 lines · 87 tokens per session scan A 9ebf9ab793e9
invoice-reconciliation is a skill published in the GitHub repository igptai/skills (16 stars, last pushed 4mo ago), licensed MIT. It adds 87 tokens to every session and 1,311 once invoked, about $0.0004 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
defi-protocol-templates
Implement DeFi protocols with production-ready templates for staking, AMMs, governance, and flash loans. Use when building decentralized finance applications or smart contract protocols.
token-movers
Crypto market scanner and single-token analyst - movers scans top winners/losers/trending or on-chain runners with pump-risk flags; single-token produces a verdict-first deep report for one token.
distribute-tokens
Two-phase contributor rewards - plan builds a tier-priced payout from the repo's merged-PR ranking; send executes it on-chain via Bankr Wallet API with per-recipient idempotency and dry-run.
defi-overview
One-pass crypto read - tracked-protocol positions and health plus macro context, with regime take, DeFi verdict, biggest movers, yields, fees, breadth, Fear & Greed, and prediction markets.
monitor-polymarket
Monitor Polymarket and/or Kalshi prediction markets for 24h price moves, volume changes, fresh comments, and high-conviction alerts.
price-alert
Fire when the tracked token does something - new ATH, sharp 1h move, or operator-set target crossed. Silent on normal days.