ramp-approvals

ramp-approvals is a command for coding agents from ramp-public/cursor-plugin. It costs 18 tokens per session (201 once invoked), scanned A, original, MIT.

A command for reviewing everything waiting for your approval in Ramp, a company spending and payments system. It combines pending transactions, bills, reimbursements, and purchase or fund requests.

In plain words
What is it for?
Use it to see pending approvals, sort them by amount, review totals, and approve or reject selected items with the required checks.
Why use it?
It gathers separate approval lists into one queue, so items are easier to review and prioritize. It also requires details and confirmation before actions are taken.

Command

Install

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.

agentmods
npx agentmods add commands/ramp-public/cursor-plugin/ramp-approvals
Clone the repo
git clone --depth 1 https://github.com/ramp-public/cursor-plugin

Wrote 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.

agentmods badge for ramp-approvals

README.md
[![agentmods](https://agentmods.dev/badge/commands/ramp-public/cursor-plugin/ramp-approvals.svg)](https://agentmods.dev/commands/ramp-public/cursor-plugin/ramp-approvals)
Your own site
<a href="https://agentmods.dev/commands/ramp-public/cursor-plugin/ramp-approvals"><img src="https://agentmods.dev/badge/commands/ramp-public/cursor-plugin/ramp-approvals.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 201 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00201
Opus 5 $0.00009 $0.00101
Sonnet 5 $0.00004 $0.00040
Haiku 4.5 $0.00002 $0.00020

Measured 5d ago against content hash 154264c6a564, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

ramp-approvals 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.

commands/ramp-approvals.md · 22 lines

What it actually says

/ramp-approvals

Review and act on everything awaiting your approval in Ramp.

Use the approval-dashboard skill to:

  1. Fetch every pending queue and paginate each to completion — pending transactions, bills, reimbursements, and requests (POs / fund requests).
  2. Present a single combined queue sorted by highest dollar amount first, grouped by type, with a total. Convert amounts correctly (transactions are formatted strings, bills and reimbursements are numeric dollars).
  3. For any item the user wants to act on, fetch full details first, then confirm before executing. Rejections must include a clear reason. Never blind-approve, and confirm before any bulk action.

Follow the steps and tool/command syntax defined in the approval-dashboard skill, and the ramp-safety guardrails for all write actions.

Changes

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.

  1. 5d ago First seen · 22 lines · 18 tokens per session scan A 154264c6a564

Subscribe to this mod's changes

ramp-approvals is a command published in the GitHub repository ramp-public/cursor-plugin (1 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 201 once invoked, about $0.0001 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.