brighty-invoice-pay

brighty-invoice-pay is a skill for Claude Code from razz-team/brighty-agent-toolkit. It costs 153 tokens per session (2,751 once invoked), scanned A, original, MIT.

A Brighty workflow that reads one invoice from a PDF, image, screenshot, email, or pasted text and prepares its payment.

In plain words
What is it for?
Use it to extract bank or crypto payment details, choose a source account, show the final fields for approval, and create one supplier-invoice transfer.
Why use it?
It reduces manual copying of recipient and payment details while requiring a clear confirmation before money is sent.

Skill for Claude Code

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

Part of the brighty plugin — 4 skills, 1 MCP server shipped together

Good fit Use it to extract bank or crypto payment details, choose a source account, show the final fields for approval, and create one supplier-invoice transfer.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/razz-team/brighty-agent-toolkit/brighty-invoice-pay
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 razz-team/brighty-agent-toolkit --skill brighty-invoice-pay
Clone the repo
git clone --depth 1 https://github.com/razz-team/brighty-agent-toolkit

Made for: Claude Code.

Or install brighty, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

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 brighty-invoice-pay

README.md
[![agentmods](https://agentmods.dev/badge/skills/razz-team/brighty-agent-toolkit/brighty-invoice-pay/github.svg)](https://agentmods.dev/skills/razz-team/brighty-agent-toolkit/brighty-invoice-pay)
Your own site
<a href="https://agentmods.dev/skills/razz-team/brighty-agent-toolkit/brighty-invoice-pay"><img src="https://agentmods.dev/badge/skills/razz-team/brighty-agent-toolkit/brighty-invoice-pay/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 brighty-invoice-pay

Your own site · 80×15
<a href="https://agentmods.dev/skills/razz-team/brighty-agent-toolkit/brighty-invoice-pay"><img src="https://agentmods.dev/badge/skills/razz-team/brighty-agent-toolkit/brighty-invoice-pay.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,751 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 $0.00153 $0.02751
Opus 5 $0.00077 $0.01375
Sonnet 5 $0.00031 $0.00550
Haiku 4.5 $0.00015 $0.00275

Measured 8d ago against content hash 74d90c913078, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

brighty-invoice-pay 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.

skills/brighty-invoice-pay/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brighty Invoice Pay

End-to-end pipeline to pay a single invoice from a document or pasted bank details. This skill does not introduce new MCP tools — it orchestrates the existing payout tools (brighty_list_accounts, brighty_create_payout, brighty_create_external_transfer, brighty_get_payout, brighty_start_payout) around an extraction + explicit confirmation step so the user always sees the final field map before any money moves.

Activate this skill when the user shares one invoice (PDF, image, screenshot, forwarded email, or pasted text) and asks to pay it. For multi-recipient CSV/Excel runs use brighty-payouts instead — that skill is built around batches.

Tools used

This skill calls only existing tools; it does not register new ones.

  • brighty_list_accounts (banking) — pick the source account when the user did not name one. Filter the returned array client-side by balance.currency to match the invoice (the API has no currency query param).
  • brighty_create_payout (payouts) — open a CREATED container with a descriptive name, e.g. "Pay AWS invoice 4321". Capture the returned id AND createdAt — both are required by every follow-up call.
  • brighty_create_external_transfer (payouts) — add the single transfer. beneficiary.kind: "FIAT" for IBAN/BIC/account-number rails; beneficiary.kind: "CRYPTO" for on-chain addresses. Pass payoutCreatedAt (the value captured above) — the Brighty API rejects without it.
  • brighty_get_payout (payouts) — re-fetch the payout immediately before the confirmation step so the user sees what Brighty stored. Pass payoutId + createdAt.
  • brighty_start_payout (payouts) — final commit. Pass payoutId + createdAt. Runs the local preflight balance check; surface its shortfalls verbatim if it fails. Returns { ok: true } on success.

Reference material

  • references/INVOICE_FIELDS.md — exact list of fields to extract from the invoice and how each maps onto brighty_create_external_transfer arguments.
  • references/CONFIRMATION_TEMPLATE.md — the shape of the message to show the user before calling brighty_start_payout. Do not skip it.

Read the full file on GitHub · 231 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 231 lines · 153 tokens per session scan A 74d90c913078

Subscribe to this mod's changes

brighty-invoice-pay is a skill published in the GitHub repository razz-team/brighty-agent-toolkit (2 stars, last pushed 27d ago), licensed MIT. It adds 153 tokens to every session and 2,751 once invoked, about $0.0008 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.