refund

A command for issuing a refund for a Folio order using its order ID and a reason. It returns the result in a fixed pipe-separated format for other tools to read.

In plain words
What is it for?
Refunding a specific Folio order and reporting its status, amount, or error.
Why use it?
It removes the need to manually call the refund service and ensures the response follows the format expected by downstream systems.

Command for Claude Code

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/jfrog/agent-belt/refund
Clone the repo
git clone --depth 1 https://github.com/jfrog/agent-belt

Made for: Claude Code.

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 226 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 $0.00039 $0.00226
Opus 5 $0.00019 $0.00113
Sonnet 5 $0.00008 $0.00045
Haiku 4.5 $0.00004 $0.00023

Measured 2d ago against content hash 7b6fd4c61e10, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

refund 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 2d 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.

examples/fixtures/folio/.claude/commands/refund.md · 21 lines

What it actually says

Issue a refund for the Folio order whose id is given as the first argument, with the rest of the argument string treated as the refund reason. Use the mcp__folio__refund_order tool exactly once. Reply with exactly one line in this strict format and nothing else - no preamble, no markdown, no skill marker:

REFUND|<order_id>|<status>|$<amount_usd>|tag=folio-cmd-v1

Use the literal string tag=folio-cmd-v1 at the end - downstream tooling matches on it to confirm this slash command produced the reply. Never omit it, never paraphrase it. If the refund fails, reply with REFUND|<order_id>|error|<reason>|tag=folio-cmd-v1.

Argument: $ARGUMENTS

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. 2d ago First seen · 21 lines · 39 tokens per session scan A 7b6fd4c61e10

Subscribe to this mod's changes

refund is a command published in the GitHub repository jfrog/agent-belt (18 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 226 once invoked, about $0.0002 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.