# Adform Budget Risk Monitor

> >-

- **Type:** Skill
- **Install:** `agentstack add skill-adform-agentic-skills-adform-budget-risk-monitor`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [adform](https://agentstack.voostack.com/s/adform)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [adform](https://github.com/adform)
- **Source:** https://github.com/adform/agentic-skills/tree/main/dist/generic/adform-budget-risk-monitor
- **Website:** https://site.adform.com

## Install

```sh
agentstack add skill-adform-agentic-skills-adform-budget-risk-monitor
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Adform budget risk monitor

Sweeps orders under a campaign, compares planned vs current vs projected delivery, and flags
two risks: under-delivery (budget left on the table) and overspend (on track to exceed budget
before the end date). Read-only.

## Connection & tooling

Runs on the Adform GraphQL MCP. Use `graphql_execute` to run queries. Keep calls sequential
(~1–2s apart).

---

## Step 1 — List orders

```graphql
{
  orders(
    campaignId: "3993873"
    active: true
    offset: 0
    limit: 20
  ) {
    orders { id name startDate endDate budget active }
    totalCount
  }
}
```

## Step 2 — Delivery indications per order

Run once per order ID:

```graphql
{
  orderDeliveryIndications(id: "67890") {
    status goalType
    effectiveFlightTotalGoal
    effectiveFlightCurrentDelivery
    effectiveFlightProjectedDelivery
    effectiveFlightRemainingDelivery
    effectiveFlightDeviationPercentage
    effectiveFlightTotalCost
    effectiveFlightDailyCost
    effectiveBudgetFlightStartDate
    effectiveBudgetFlightEndDate
  }
}
```

## Step 3 — Campaign-level view (optional)

```graphql
{
  campaignDeliveryIndications(id: "3993873") {
    status goalType
    effectiveFlightTotalGoal effectiveFlightCurrentDelivery
    effectiveFlightProjectedDelivery effectiveFlightDeviationPercentage
    effectiveFlightTotalCost effectiveFlightDailyCost
  }
}
```

## Step 4 — Daily trend for at-risk entities (optional)

Max 30-day window per call:

```graphql
{
  orderDailyDeliveryIndications(
    ids: ["67890", "67891"]
    from: "2026-05-13"
    until: "2026-06-12"
  ) {
    id deliveryDate
    deliveryIndications { effectiveFlightDailyCost effectiveFlightDeviationPercentage status }
  }
}
```

---

## Reading the results

- **Under-delivery risk**: `effectiveFlightProjectedDelivery` materially below
  `effectiveFlightTotalGoal` (negative deviation beyond your threshold, e.g. −10%) while
  the flight is active — reallocation candidate
- **Overspend risk**: deviation strongly positive, or daily cost trend implies budget exhaustion
  before end date
- **Schedule gap**: `status: ScheduleGap` — currently outside an active flight, not a risk in
  itself unless the gap is unexpected

---

## Presenting

Risk table: entity (order or campaign), budget goal, current spend, projected spend, deviation
%, and a verdict — UNDER-DELIVERING, OVER-DELIVERING, or ON TRACK. Lead with at-risk entities
and the monetary amount in play. Suggest reallocating from under-delivering to over-delivering
orders where it fits the plan. For a single entity's detailed pacing use adform-pacing-check;
for a blocked entity use adform-delivery-health.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [adform](https://github.com/adform)
- **Source:** [adform/agentic-skills](https://github.com/adform/agentic-skills)
- **License:** MIT
- **Homepage:** https://site.adform.com

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-adform-agentic-skills-adform-budget-risk-monitor
- Seller: https://agentstack.voostack.com/s/adform
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.