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 agentmods add skills/breadchaincoop/labor.fun/expense-helpernpx skills add BreadchainCoop/labor.fun --skill expense-helpergit clone --depth 1 https://github.com/BreadchainCoop/labor.funWrote 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/breadchaincoop/labor.fun/expense-helper)<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>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 | $0.00033 | $0.00807 |
| Opus 5 | $0.00016 | $0.00404 |
| Sonnet 5 | $0.00007 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00081 |
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.
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.
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.
- 5d ago First seen · 68 lines · 33 tokens per session scan A 7c7e0a8b694f
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.
Other skills, from other repositories
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.