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 DjangoPeng/agentic-ai --skill financial-expense-automationgit clone --depth 1 https://github.com/DjangoPeng/agentic-aiWrote 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/djangopeng/agentic-ai/financial-expense-automation)<a href="https://agentmods.dev/skills/djangopeng/agentic-ai/financial-expense-automation"><img src="https://agentmods.dev/badge/skills/djangopeng/agentic-ai/financial-expense-automation/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/djangopeng/agentic-ai/financial-expense-automation"><img src="https://agentmods.dev/badge/skills/djangopeng/agentic-ai/financial-expense-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00100 | $0.01632 |
| Opus 5 | $0.00050 | $0.00816 |
| Sonnet 5 | $0.00020 | $0.00326 |
| Haiku 4.5 | $0.00010 | $0.00163 |
Grade A, and why
financial-expense-automation 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Financial Expense Automation
目标
运行本地 Financial Automation 流水线,对用户上传的报销票据进行:
- 识别
- 结构化提取
- 校验
- 真实写入飞书多维表格
请始终记住:
bitable_write_plan只是中间产物- 识别成功不等于任务完成
- 只有真实调用 Feishu Bitable
create/update成功,并完成回读确认,才算完成
项目依赖
这个 skill 依赖完整项目仓库,不能只拷贝 SKILL.md 单独使用。
按以下顺序定位项目根目录:
- 环境变量
FINANCIAL_AUTOMATION_ROOT ~/projects/agentic-ai/financial-automation~/.openclaw/workspace/financial-automation
若这些路径都不存在,应明确告诉用户:当前环境尚未部署完整项目仓库,请先完成部署。
主要入口与配置:
<repo_root>/src/skill_entry.py<repo_root>/config/app_config.yaml
支持输入
附件输入格式:
[
{"file_name": "hotel_invoice.pdf", "content_bytes": b"..."},
{"file_name": "ticket.jpg", "source_path": "/path/to/ticket.jpg"},
]
支持文件类型:
.pdf.jpg.jpeg.png
若过滤后没有可处理附件,应直接告知用户:没有收到可处理的报销附件。
非报销内容处理
识别完成后,若内容不是报销票据(如普通图片、截图、合同等),应:
- 告知用户:该附件不是可识别的报销票据
- 简述识别到的内容类型
- 终止流程,不继续写表
唯一入口
必须通过:
from src.skill_entry import run_skill_job
result = run_skill_job(attachments)
如有需要可显式传配置:
result = run_skill_job(
attachments,
config_path=f"{repo_root}/config/app_config.yaml",
)
不要手工拼接 ingest / OCR / validate / formatter 流程。
正式执行流程
- 定位 repo root
- 将用户上传文件整理成
run_skill_job(...)所需的附件 payload - 调用
run_skill_job(...) - 使用返回的
skill_result作为识别结果主对象 - 生成真实写表输入
- 若当前会话具备 Feishu Bitable 工具能力,继续执行真实写表
- 写入后回读确认,再向用户回复结果
写表强制规则
bitable_write_plan只是中间产物,不是最终结果- 只要当前会话可用飞书多维表格工具,就必须继续真实写表
- 禁止停留在“建议写入 / 准备写入 / 可写入”状态
- 只有真正调用
create/update成功,才算完成 - 如果没有真实写入成功,必须明确说明失败点
- 禁止把“已识别 / 已生成 plan / 已生成 handoff”描述成已经完成落表
目标表路由规则
transportation_fee→交通报销表- 其他费用类票据 →
费用报销表
写入策略
默认采用:
update_first_blank_row_then_create
具体规则:
- 先查询目标表
- 若存在可复用空白行(优先判断
doc_id为空),优先update - 若不存在可复用空白行,再
create - 不要盲目追加新记录
附件写入规则
附件字段必须遵守以下规则:
- 禁止直接使用通用 Drive upload token 作为 Bitable 附件
- 必须先上传到当前 bitable attachment context
- 再将返回的合法
file_token写入附件字段 - 图片走
bitable_image - PDF/其他文件走
bitable_file
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 · 200 lines · 100 tokens per session scan A d7105d4dc99f
financial-expense-automation is a skill published in the GitHub repository DjangoPeng/agentic-ai (148 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 1,632 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
pdf-reader
PDF content extraction and analysis specialist.
report-generator
Generate professional HTML/PDF investment reports with interactive visualizations.
add-pdf-reader
Add PDF reading to ClaudeClaw agents. Extracts text from PDFs via pdftotext CLI. Handles WhatsApp attachments, URLs, and local files.
receipts-to-expenses
Read a batch of receipt images directly via vision, classify each into expense categories, optionally reconcile against a bank statement CSV, and produce a multi-sheet Excel workbook + a PDF summary. Use when given receipt photos and asked for an expense report.
research-to-diagram
A workflow that researches a topic on the internet, organizes the findings, and produces a visual relationship map as a PDF.
docx
Read, create, and convert Microsoft Word (.docx) documents — extract text and tables, build reports from markdown/JSON, and export to PDF.