card-management

card-management is a skill for Claude Code, Codex from ramp-public/cursor-plugin. It costs 135 tokens per session (1,241 once invoked), scanned A, original, MIT.

A terminal-based tool for viewing a user's cards, checking their states, and activating or locking and unlocking them.

In plain words
What is it for?
Use it to list cards, count or filter active cards, check card status, activate a card, or lock and unlock one.
Why use it?
It separates a card's lifecycle state from its physical activation status and handles filtering when the service cannot filter by state itself.

Skill for Claude CodeCodex

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 skills/ramp-public/cursor-plugin/card-management
Any agent
npx skills add ramp-public/cursor-plugin --skill card-management
Clone the repo
git clone --depth 1 https://github.com/ramp-public/cursor-plugin

Made for: Claude Code, Codex.

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 card-management

README.md
[![agentmods](https://agentmods.dev/badge/skills/ramp-public/cursor-plugin/card-management.svg)](https://agentmods.dev/skills/ramp-public/cursor-plugin/card-management)
Your own site
<a href="https://agentmods.dev/skills/ramp-public/cursor-plugin/card-management"><img src="https://agentmods.dev/badge/skills/ramp-public/cursor-plugin/card-management.svg" alt="Measured on agentmods" height="20"></a>
Per session 135 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,241 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 $0.00135 $0.01241
Opus 5 $0.00068 $0.00620
Sonnet 5 $0.00027 $0.00248
Haiku 4.5 $0.00014 $0.00124

Measured 5d ago against content hash bb1ea0a1aacc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

card-management 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.

skills/card-management/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Non-Negotiables

  • To list cards, use ramp cards list — NOT ramp funds list (that lists funds/budgets, not cards).
  • The API has no server-side state filter. To count or filter by state, list all cards, then filter on card_state client-side.
  • Pass --agent for machine-readable JSON output whenever you need to count or filter programmatically.
  • card_state is a free-form string from the API with no fixed enum in the spec; active cards report a card_state that equals active case-insensitively (e.g. ACTIVE). Always compare case-insensitively and report exactly what the API returns; do not invent states.
  • A card's lifecycle state (card_state) is distinct from its activation_status (whether the physical card has been activated). A card can be active while still not_activated for physical use.

Workflow

Step 1: List the cards

ramp cards list --rationale "list the user's cards" --agent

In --agent mode the response is wrapped in the standard envelope: the cards live in the nested array at .data[0].cards[] (not one card per .data[]). Each card object includes display_name, last_four, card_state, activation_status, card_type, is_physical, and id.

Admins and managers can target another employee's cards by passing that user's UUID — run ramp cards list --help to confirm the option is available in your synced spec.

Step 2: Count or filter by state

Count active cards directly with jq. The cards are at .data[0].cards[], and card_state casing is compared case-insensitively so it works regardless of how the API capitalizes it:

ramp cards list --rationale "count active cards" --agent | jq '[.data[0].cards[] | select((.card_state // "" | ascii_downcase) == "active")] | length'

List just the active card names:

ramp cards list --rationale "list active cards" --agent | jq -r '.data[0].cards[] | select((.card_state // "" | ascii_downcase) == "active") | .display_name'

In a human terminal, ramp cards list shows card_state and activation_status as columns, so you can count active cards by eye.

Read the full file on GitHub · 98 lines

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 · 98 lines · 135 tokens per session scan A bb1ea0a1aacc

Subscribe to this mod's changes

card-management is a skill published in the GitHub repository ramp-public/cursor-plugin (1 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 1,241 once invoked, about $0.0007 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.