For AI agents: Markdown version of this page · llms.txt
Setup guide

Spend Request Agent for Hermes

The $19 Spend Request Agent runs on Hermes as three plain-text files: set it up once in your Hermes workspace, approve a sample-data test, then trigger each run with the usage prompt and this run's inputs.

Get the Spend Request Agent - $19Hermes overview

What the Spend Request Agent does

On Hermes, this agent's files and outputs stay entirely on your machine. It normalizes incoming spend requests and runs your policy and evidence checks: request, amount, policy check, evidence, approver and status. Approvals become one review, not a reconstruction.

Spend requests arrive by email, chat and the occasional hallway ask. Policy checks happen in someone's head, and audit season reconstructs decisions nobody wrote down.

Where the three files go in Hermes

Give Hermes the three files in its workspace: skill.md becomes the standing skill, then run the setup prompt and approve the fictional-data test. Because Hermes is open-source and local-first, your prompts and outputs stay under your control.

What a run looks like on Hermes

A run looks like this: you ask Hermes to run spend-approvals with this run's inputs, and it works through the workspace skill. The output - it normalizes incoming spend requests and runs your policy and evidence checks: request, amount, policy check, evidence, approver and status - is written to your own workspace for review.

Setup, step by step

  1. Place skill.md in your Hermes workspace as the standing skill for the job (for example: spend approvals).
  2. Run setup-prompt.txt; the agent runs spend-approvals on fictional sample data first - approve that test before real work.
  3. Hermes is local-first and open-source, so the prompts, files and outputs stay under your control.
  4. Trigger each real run with usage-prompt.txt and this run's inputs; the workspace persists between asks.

Honest limits on Hermes

Hermes is a young, fast-moving open-source project. Expect rough edges, and verify its current file-handling in its own docs before a big setup.

Questions people ask

Does the Spend Request Agent work on Hermes?

Yes - the agent is three plain-text files, and on Hermes they live in your Hermes workspace. The four setup steps below are the whole job: Place skill.md in your Hermes workspace as the standing skill for the job (for example: spend approvals). Then run setup-prompt.txt; the agent runs spend-approvals on fictional sample data first - approve that test before real work.

What does the Spend Request Agent produce on Hermes?

It normalizes incoming spend requests and runs your policy and evidence checks: request, amount, policy check, evidence, approver and status. Hermes writes it into your own workspace - nothing leaves your machine. Every run waits for your approval before anything is sent, spent, published or scheduled.

Is this affiliated with Hermes?

No. AI Agent Skills is an independent store. We are not affiliated with, endorsed by, or sponsored by Hermes or its makers. Platform names belong to their owners; capabilities change, so check Hermes's current documentation.

Run this agent on another assistant

Instinct Claude Gemini OpenClaw ChatGPT Grok DeepSeek Perplexity Microsoft Copilot Town Muse

More finance teams agents on Hermes

Cash Flow Forecast Agent Budget Variance Agent Management Reporting Agent

AI Agent Skills is an independent store, not affiliated with Hermes or its makers. Platform names belong to their owners.