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 Bwkyd/wps-skills --skill wps-budgetgit clone --depth 1 https://github.com/Bwkyd/wps-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/bwkyd/wps-skills/wps-budget)<a href="https://agentmods.dev/skills/bwkyd/wps-skills/wps-budget"><img src="https://agentmods.dev/badge/skills/bwkyd/wps-skills/wps-budget/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/bwkyd/wps-skills/wps-budget"><img src="https://agentmods.dev/badge/skills/bwkyd/wps-skills/wps-budget.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 | $0.00082 | $0.02056 |
| Opus 5 | $0.00041 | $0.01028 |
| Sonnet 5 | $0.00016 | $0.00411 |
| Haiku 4.5 | $0.00008 | $0.00206 |
Grade A, and why
wps-budget 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
预算表/费用表生成器
选类型 → 填数据 → 自动公式 → 预算表搞定。
When to Use
- 制作年度/季度/月度预算表
- 项目预算编制
- 活动经费预算
- 预算执行情况分析
- 用户说"帮我做预算表""编制费用预算"
When NOT to Use
- 工资核算 → 使用
wps-salary - 财务报表 → 使用
wps-financial-report
预算模板类型
[1] 部门年度预算 → 人力/办公/差旅/培训等分项
[2] 项目预算 → 人工/材料/设备/外包/管理费
[3] 活动预算 → 场地/餐饮/物料/交通/宣传
[4] 家庭预算 → 收入/固定支出/可变支出/储蓄
[5] 营销预算 → 线上/线下/品牌/效果/公关
工作流程
Step 1: 确认预算要素
- 预算类型:部门/项目/活动
- 时间范围:年度/季度/月度
- 预算分类:需要哪些费用项
- 是否需要对比:预算vs实际
Step 2: 生成预算表
from openpyxl import Workbook
from openpyxl.styles import Font, Alignment, PatternFill, Border, Side, numbers
from openpyxl.utils import get_column_letter
import os
def create_budget(budget_type, items, output_path=None):
"""生成预算表"""
wb = Workbook()
ws = wb.active
ws.title = "预算表"
# 样式
header_fill = PatternFill('solid', fgColor='2C3E50')
header_font = Font(name='微软雅黑', size=11, bold=True, color='FFFFFF')
cat_fill = PatternFill('solid', fgColor='ECF0F1')
cat_font = Font(name='微软雅黑', size=11, bold=True)
body_font = Font(name='微软雅黑', size=10)
money_fmt = '#,##0.00'
pct_fmt = '0.0%'
thin = Side(style='thin')
border = Border(left=thin, right=thin, top=thin, bottom=thin)
# 标题
ws.merge_cells('A1:G1')
ws['A1'] = f"{'部门' if budget_type=='dept' else '项目'}预算表"
ws['A1'].font = Font(name='微软雅黑', size=16, bold=True)
ws['A1'].alignment = Alignment(horizontal='center')
# 表头
headers = ['序号', '费用类别', '费用项目', '预算金额',
'实际金额', '差异', '执行率']
for col, h in enumerate(headers, 1):
cell = ws.cell(row=3, column=col, value=h)
cell.font = header_font
cell.fill = header_fill
cell.alignment = Alignment(horizontal='center')
cell.border = border
# 列宽
widths = [6, 14, 20, 14, 14, 14, 10]
for i, w in enumerate(widths, 1):
ws.column_dimensions[get_column_letter(i)].width = w
# 填入数据
row = 4
seq = 1
for category, sub_items in items.items():
# 分类行
ws.merge_cells(start_row=row, start_column=2,
end_row=row, end_column=3)
ws.cell(row=row, column=1, value='').border = border
cat_cell = ws.cell(row=row, column=2, value=category)
cat_cell.font = cat_font
cat_cell.fill = cat_fill
cat_cell.border = border
# 分类小计公式
start = row + 1
end = row + len(sub_items)
for c in [4, 5]:
cell = ws.cell(row=row, column=c)
cell.value = f'=SUM({get_column_letter(c)}{start}:{get_column_letter(c)}{end})'
cell.number_format = money_fmt
cell.font = cat_font
cell.fill = cat_fill
cell.border = border
# 差异和执行率
ws.cell(row=row, column=6,
value=f'=D{row}-E{row}').number_format = money_fmt
ws.cell(row=row, column=6).fill = cat_fill
ws.cell(row=row, column=6).border = border
ws.cell(row=row, column=7,
value=f'=IF(D{row}=0,"",E{row}/D{row})').number_format = pct_fmt
ws.cell(row=row, column=7).fill = cat_fill
ws.cell(row=row, column=7).border = border
row += 1
for item_name, amount in sub_items.items():
ws.cell(row=row, column=1, value=seq).border = border
ws.cell(row=row, column=1).font = body_font
ws.cell(row=row, column=3, value=item_name).border = border
ws.cell(row=row, column=3).font = body_font
ws.cell(row=row, column=4, value=amount).border = border
ws.cell(row=row, column=4).number_format = money_fmt
ws.cell(row=row, column=5, value=0).border = border
ws.cell(row=row, column=5).number_format = money_fmt
ws.cell(row=row, column=6,
value=f'=D{row}-E{row}').number_format = money_fmt
ws.cell(row=row, column=6).border = border
ws.cell(row=row, column=7,
value=f'=IF(D{row}=0,"",E{row}/D{row})').number_format = pct_fmt
ws.cell(row=row, column=7).border = border
seq += 1
row += 1
# 合计行
ws.merge_cells(start_row=row, start_column=1,
end_row=row, end_column=3)
total_cell = ws.cell(row=row, column=1, value='合计')
total_cell.font = Font(name='微软雅黑', size=12, bold=True)
total_cell.alignment = Alignment(horizontal='center')
total_cell.fill = PatternFill('solid', fgColor='3498DB')
total_cell.font = Font(name='微软雅黑', size=12, bold=True, color='FFFFFF')
for c in [4, 5, 6]:
cell = ws.cell(row=row, column=c)
cell.value = f'=SUMPRODUCT(({get_column_letter(c)}4:{get_column_letter(c)}{row-1})*(A4:A{row-1}<>""))'
cell.number_format = money_fmt
cell.font = Font(name='微软雅黑', bold=True, color='FFFFFF')
cell.fill = PatternFill('solid', fgColor='3498DB')
cell.border = border
if not output_path:
output_path = '预算表.xlsx'
wb.save(output_path)
return os.path.abspath(output_path)
What ships with it
1 file 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.
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 · 212 lines · 82 tokens per session scan A 08e127b00632
wps-budget is a skill published in the GitHub repository Bwkyd/wps-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 2,056 once invoked, about $0.0004 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
cwicr-report-generator
Generate professional cost estimation reports from CWICR calculations. HTML, PDF, Excel outputs with charts and breakdowns.
xlsx-financials
Produce formatted .xlsx financial statement workbooks from XBRL statement data. Uses Bash + openpyxl (Python) following Anthropic FSI xlsx-author conventions for professional Excel output with calculation arc cross-validation.
audit-xls
Audit spreadsheet, formula error detection, hardcoded cell finder, cross-sheet reference audit, workbook auditor, Excel model audit, financial model QA, spreadsheet review, cell dependency trace, formula integrity check.
issue-invoice
Fill a monthly hourly invoice on Google Sheets from GitHub PRs and Jira tickets, one tab per month per client. Use when the user mentions an invoice, timesheet, billable hours, logging monthly work, rolling over an invoice month, or reconciling PRs and tickets to hours.
income-tax-hometax
A Korean workflow for comprehensive income-tax filing through Hometax, South Korea's online tax service. It covers income checks, expense methods, deductions, spreadsheet reconciliation, and final review before submission.
receipt-classify-kr
A tool for classifying receipts, card payments, and cash expenses for businesses in South Korea. It suggests accounting categories and identifies possible VAT and income-tax treatment.