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 lossless-group/lossless-agent-skills --skill expense-report-generationgit clone --depth 1 https://github.com/lossless-group/lossless-agent-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/lossless-group/lossless-agent-skills/expense-report-generation)<a href="https://agentmods.dev/skills/lossless-group/lossless-agent-skills/expense-report-generation"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/expense-report-generation/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/lossless-group/lossless-agent-skills/expense-report-generation"><img src="https://agentmods.dev/badge/skills/lossless-group/lossless-agent-skills/expense-report-generation.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 | $0.00181 | $0.03121 |
| Opus 5 | $0.00090 | $0.01561 |
| Sonnet 5 | $0.00036 | $0.00624 |
| Haiku 4.5 | $0.00018 | $0.00312 |
Grade A, and why
expense-report-generation 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 11d 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expense Report Generation
Statement data is not an expense report. The gap between them is identification, categorisation, and disclosure — and every one of those is where a claim gets rejected. This skill is the path across.
The deliverable is a document a client's finance team can approve without asking a single question. Every line names what it bought. Nothing is silently dropped. Nothing is silently included.
1. Where the data lives
Statements are financial records. They go in a gitignored directory — never in tracked source. The working layout:
private-data/lossless/reimbursable-expenses/
├── amex-business/ statement CSVs + PDFs
├── bank-<institution>-<year>/ bank statement PDFs + .txt extractions
├── receipts/ per-charge receipts (PDF/email exports)
├── reports/ generated CSVs, HTML, PDF
├── _all-amex-<year>.csv merged transactions, with a Statement column
├── _<bank>-debits.csv parsed bank debits
└── build_*.py the generators
Generate, never hand-edit. Every report is built by a script from the merged data. A hand-edited CSV cannot be rebuilt when a line changes, and the figures drift from the source. Categorisation rules live in the script so a rebuild is deterministic.
Account-to-card mappings, confirmed-personal vendors, and letterhead contact details are instance facts — they belong in the private folder and in agent memory, not in this committed skill.
2. Merge before you analyse
Statement CSVs are per-billing-period. Merge them into one file with a Statement
column before doing anything else, or you will reason about a partial window.
Two traps in the merge:
- Dates sort wrong as strings.
MM/DD/YYYYstring-sorted puts 01/01/2026 before 12/31/2025. Parse to real dates before sorting or taking a range. - Credits are not expenses. Payments (
MOBILE PAYMENT - THANK YOU), refunds, and statement credits net against charges and will silently deflate a total. Filter toamount > 0and report the two figures separately.
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.
- 11d ago First seen · 307 lines · 181 tokens per session scan A 2f4f3f54a417
expense-report-generation is a skill published in the GitHub repository lossless-group/lossless-agent-skills (4 stars, last pushed 18d ago), licensed MIT. It adds 181 tokens to every session and 3,121 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
steuer-assistent
Points to the standalone module steuer-assistent: a local, offline-first receipt worksheet for German employee income-related expenses (Werbungskosten) -- record, sum to the cent, private ZIP export. Use this skill when Werbungskosten receipts should be prepared in a structured way -- with a clear boundary: not tax…
monthly-close-checklist-and-reconciliation-prep
A bookkeeping preparation skill that turns a pasted bank export or transaction list into a monthly-closing checklist, draft categories with disputed items marked, and a summary for an accountant or investor.
xlsx-toolkit
Audit Microsoft Excel (.xlsx) workbooks for formula density, external references, named ranges, hidden sheets, and data validation. Use when reviewing a financial model, sharing a workbook externally, or checking for data leakage.
datapack-builder
Build professional financial services data packs from various sources including CIMs, offering memorandums, SEC filings, web search, or MCP servers. Extract, normalize, and standardize financial data into investment committee-ready Excel workbooks with consistent structure, proper formatting, and documented…
lbo-model
This skill should be used when completing LBO (Leveraged Buyout) model templates in Excel for private equity transactions, deal materials, or investment committee presentations. The skill fills in formulas, validates calculations, and ensures professional formatting standards that adapt to any template structure.
sheet-model
Headless spreadsheet engine for financial modeling, data analysis, and scenario comparison. Use when: building financial models with ratios and what-if scenarios, computing derived values from tabular data with formulas, producing .xlsx files with live formulas (not static values) for human review, any task where the…