expense-helper

expense-helper is a skill for Claude Code, Codex from BreadchainCoop/labor.fun. It costs 33 tokens per session (807 once invoked), scanned A, original, MIT.

An expense-request and reimbursement guide for handling planned spending, receipts, approvals, and repayment. Reimbursement means getting money back for a purchase you already paid for.

In plain words
What is it for?
Use it for new expense requests, receipt submissions, retrospective reimbursement claims, and converting dollar amounts into cents for submission.
Why use it?
It helps choose the correct process based on whether spending is planned or already happened, while checking amounts before submission.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/breadchaincoop/labor.fun/expense-helper
Any agent
npx skills add BreadchainCoop/labor.fun --skill expense-helper
Clone the repo
git clone --depth 1 https://github.com/BreadchainCoop/labor.fun

Made for: Claude Code, Codex.

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 expense-helper

README.md
[![agentmods](https://agentmods.dev/badge/skills/breadchaincoop/labor.fun/expense-helper.svg)](https://agentmods.dev/skills/breadchaincoop/labor.fun/expense-helper)
Your own site
<a href="https://agentmods.dev/skills/breadchaincoop/labor.fun/expense-helper"><img src="https://agentmods.dev/badge/skills/breadchaincoop/labor.fun/expense-helper.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 807 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00033 $0.00807
Opus 5 $0.00016 $0.00404
Sonnet 5 $0.00007 $0.00161
Haiku 4.5 $0.00003 $0.00081

Measured 5d ago against content hash 7c7e0a8b694f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

expense-helper 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 5d 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.

container/skills/expense-helper/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Expense Helper

Choosing the right path

  • Prospective is always preferred. If the user says "I'm planning to...", "I need funds for...", "Can I expense...", use request_expense.
  • Retrospective only when they've already spent. Before calling submit_retrospective_expense, always say: "The preferred flow is to request approval before spending. Please try to do that next time." Then proceed.

Disambiguation examples

User says Path Why
"I need $200 for supplies this week" prospective hasn't spent yet
"I spent $38 on ink last Tuesday, need reimbursement" retrospective past tense, already out of pocket
"Can I expense a new chair?" prospective asking permission, not reporting
"Here's the receipt for the catering you approved" submit_receipt pre-approved expense in receipt_pending

Amount formatting

  • Accept user input in dollars ($45.50, "forty-five fifty", etc.)
  • Convert to cents before calling the tool: 45.50 → 4550
  • Always echo the parsed amount back to the user for confirmation before submitting

Available tools

Tool When to use
request_expense New prospective request (preferred)
submit_retrospective_expense Backlog submission for already-spent money (discouraged)
approve_expense Approver accepts as-submitted
deny_expense Approver rejects — requires reason
modify_expense Approver accepts at a different amount (prospective only)
submit_receipt Requester attaches receipt after a purchase
process_reimbursement Finance executes the payout
cancel_expense Requester withdraws before reimbursement

Event linking

If the user mentions an event by name or the conversation context includes an event project, look up the event_id via list_events and attach it. Event budgets roll up through this field.

Receipts

  • Accept any image or PDF attachment as a receipt.
  • Store under the expense's KB doc directory if applicable, or accept an external URL.
  • Pass the path/URL as receipt_path.

Read the full file on GitHub · 68 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. 5d ago First seen · 68 lines · 33 tokens per session scan A 7c7e0a8b694f

Subscribe to this mod's changes

expense-helper is a skill published in the GitHub repository BreadchainCoop/labor.fun (2 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 807 once invoked, about $0.0002 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.