invoices-and-quotes

invoices-and-quotes is a skill for Claude Code from Frihet-io/frihet-mcp. It costs 84 tokens per session (2,358 once invoked), scanned A, original, MIT.

A business-record tool for searching invoices and preparing invoice or quote drafts in a connected Frihet workspace. It keeps saved drafts separate from issued or officially submitted documents.

In plain words
What is it for?
Use it to search and inspect invoices, review quotes, prepare invoice or quote drafts, and delete or cancel quotes.
Why use it?
It makes billing records easier to find and reduces the risk of confusing a proposal or draft with a finalized financial document. Creating or deleting records requires confirmation.

Skill for Claude Code

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

Part of the frihet-erp plugin — 5 skills, 2 MCP servers, 1 plugin shipped together

Good fit Use it to search and inspect invoices, review quotes, prepare invoice or quote drafts, and delete or cancel quotes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/frihet-io/frihet-mcp/invoices-and-quotes
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 Frihet-io/frihet-mcp --skill invoices-and-quotes
Clone the repo
git clone --depth 1 https://github.com/Frihet-io/frihet-mcp

Made for: Claude Code.

Or install frihet-erp, the plugin that ships this one along with the rest of its 5 skills, 2 MCP servers, 1 plugin.

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 invoices-and-quotes

README.md
[![agentmods](https://agentmods.dev/badge/skills/frihet-io/frihet-mcp/invoices-and-quotes/github.svg)](https://agentmods.dev/skills/frihet-io/frihet-mcp/invoices-and-quotes)
Your own site
<a href="https://agentmods.dev/skills/frihet-io/frihet-mcp/invoices-and-quotes"><img src="https://agentmods.dev/badge/skills/frihet-io/frihet-mcp/invoices-and-quotes/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 invoices-and-quotes

Your own site · 80×15
<a href="https://agentmods.dev/skills/frihet-io/frihet-mcp/invoices-and-quotes"><img src="https://agentmods.dev/badge/skills/frihet-io/frihet-mcp/invoices-and-quotes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,358 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 $0.00084 $0.02358
Opus 5.5 $0.00034 $0.00943
Sonnet 5.5 $0.00017 $0.00472
Haiku 4.5 $0.00008 $0.00236

Measured 2d ago against content hash cbdd5bf5b6cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

invoices-and-quotes 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 2d 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.

marketplace/openai/skills/invoices-and-quotes/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Invoices & Quotes (invoices-and-quotes)

Respond in the user's language (English or Spanish). Keep proposals in chat strictly separate from saved Frihet records, and keep internal draft records strictly separate from issued or fiscally submitted documents.

Supported tools in this workflow

  • Invoices (read-only): list_invoices, get_invoice, search_invoices
  • Invoices (write, requires confirm: true): create_invoice
  • Quotes (read-only): list_quotes, get_quote
  • Quotes (write, requires confirm: true): create_quote, delete_quote
  • Supporting read-only lookups: get_business_context, list_clients, get_client, list_products, get_product

1. Reading and searching invoices and quotes

  1. Choose the right read tool:
    • Use list_invoices (status, clientId, from, to, seriesId, limit, offset, after) for filtered invoice lists.
    • Use search_invoices (query, status, from, to, limit, offset, after) when searching by text query (such as client name or invoice number).
    • Use get_invoice (id) to inspect full stored line items (items), notes, discountRate, taxRate, and total for a single invoice, because list_invoices and search_invoices return summary rows without line items or notes.
    • Use list_quotes and get_quote (id) analogously for quotes.
  2. Pagination truth (never present one page as all records):
    • Always inspect total, limit, offset, and nextCursor.
    • Exploratory browsing (default): If nextCursor is present or total > data.length on a general listing/search query, report the first page immediately without looping through extra pages, and explicitly label the output as a partial page (e.g., Showing 20 of 47 invoices). Never sum a partial page and claim it is the full period total.
    • Exhaustive, full-sort, or aggregate requests (exception): When the user explicitly asks for all matching records, a full sort across the entire set, or an exact sum across all pages, paginate using after (nextCursor) or offset until all pages are retrieved (or until a clear safety limit is reached, disclosing the exact number of records fetched out of total) before computing the sort or total.
  3. Stored totals and internal status boundary:
    • Report total only when present on the returned record; if total is absent, state that the calculated total is not stored on the summary row and call get_invoice / get_quote if detail is needed.
    • Internal status and issueDate reflect workspace records only. They do not prove external email delivery, Peppol delivery receipts, EN 16931 validation, or e-invoicing (VeriFactu/AEAT/TicketBAI) submission or acceptance. If the user asks exclusively for regulated e-invoice delivery receipts or transmission status, explain that those external receipts are outside this connector without calling Frihet tools.

Read the full file on GitHub · 73 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. 2d ago First seen · 73 lines · 84 tokens per session scan A cbdd5bf5b6cd

Subscribe to this mod's changes

invoices-and-quotes is a skill published in the GitHub repository Frihet-io/frihet-mcp (12 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 2,358 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-28.