xhr-labs/agent-xhr-plugins/get-expense

Claude Code and agent skill by xhr-labs/agent-xhr-plugins

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Read one expense request in full - name, date, category, merchant, amounts, exchange rate, reimbursement, receipts, policy warnings, rejection reason, and the actions currently available on it.

Install

npx vskill@latest install xhr-labs/agent-xhr-plugins/get-expense

SKILL.md

The same SKILL.md was published earlier as xhr-labs/agent-xhr-plugins/get-expense.

Get Expense Detail

Intent: exm-get-expense

User request patterns
  • show the details of this expense
  • open my UAE Trip expense
  • why was my expense rejected
  • what is the reimbursement amount for this expense
  • show the receipt attached to this expense
  • check which policy warning this expense triggered
  • show the exchange rate used on this expense
  • what can I still do with this expense request
Retrieval tags
  • exm
  • expense-management
  • expense-detail
  • receipt
  • policy-warning
  • rejection-reason
  • reimbursement
Answer objective

Return one expense request in full so the user can see its submitted details, money breakdown, receipts, policy result, and remaining actions.

Instructions
  • --expense-id takes a UUID only. Resolve it first with skills/exm/list_my_expenses (own expense) or skills/exm/list_expense_approvals (expense awaiting the caller's approval). Never construct, guess, or reuse a remembered UUID, and never pass an employee ID as an expense ID.
  • not_found means the expense does not exist or the caller cannot see it. Say so and stop; do not retry with a different ID.
  • Present the answer as short labelled lines or a two-column table: name, expense date, category, merchant, description, amount with currency, exchange rate (only when present and different from 1), reimbursement amount with currency, status, submitted on, receipts (file names and count).
  • Render status in plain language, never the raw enum. When rejectedReason is present and the status is rejected, quote that reason verbatim; never invent a reason.
  • Multi-item expenses return an items array. Summarize each line (line number, date, category, amount) and give the expense total; do not present one line as if it were the whole expense.
  • policyResult carries the policy engine outcome. Report BLOCK as "blocked by policy" and WARN as a warning, list each violation message, and never restate a warning as a rejection.
  • Receipts are listed by file name and document type only; this tool deliberately strips storage links. Tell the user to open the expense in Expense Management to preview or download a receipt, and never fabricate a download URL.
  • Never print expense IDs, employee IDs, document IDs, or any other UUID in the reply.
  • availableActions states what the caller may still do (CANCEL, APPROVE, REJECT). Offer only the actions listed there, then use skills/exm/cancel_expense or skills/exm/manage_expense_approval.
Required arguments
  • expense_id: Expense UUID from list_my_expenses or list_expense_approvals.
Execution
text
python skills/exm/get_expense/scripts/get_expense.py --expense-id <uuid>

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
1
7-day trend score
8

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/xhr-labs/agent-xhr-plugins/get-expense/badge)](https://verified-skill.com/skills/xhr-labs/agent-xhr-plugins/get-expense)

Something wrong with this skill or its page? Tell us.