audit-creative

audit-creative is an agent for Claude Code from OrbiAds/Orbiads-GAM-MCP. It costs 48 tokens per session (609 once invoked), scanned A, original, MIT.

A subagent that checks whether active online advertisements meet technical and tracking requirements.

In plain words
What is it for?
Use it to inspect active creatives for format, size, click-tag, and SSL issues, and to audit tracking on active orders.
Why use it?
It gathers compliance problems, insecure links, and missing or inconsistent tracking into a separate report for each advertising network.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions subagents.

Part of the orbiads plugin — 8 skills, 7 commands, 5 agents, 1 hook, 2 MCP servers shipped together

Good fit Use it to inspect active creatives for format, size, click-tag, and SSL issues, and to audit tracking on active orders.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/orbiads/orbiads-gam-mcp/audit-creative
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.

Clone the repo
git clone --depth 1 https://github.com/OrbiAds/Orbiads-GAM-MCP

Made for: Claude Code.

Or install orbiads, the plugin that ships this one along with the rest of its 8 skills, 7 commands, 5 agents, 1 hook, 2 MCP servers.

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 audit-creative

README.md
[![agentmods](https://agentmods.dev/badge/agents/orbiads/orbiads-gam-mcp/audit-creative/github.svg)](https://agentmods.dev/agents/orbiads/orbiads-gam-mcp/audit-creative)
Your own site
<a href="https://agentmods.dev/agents/orbiads/orbiads-gam-mcp/audit-creative"><img src="https://agentmods.dev/badge/agents/orbiads/orbiads-gam-mcp/audit-creative/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for audit-creative

Your own site · 80×15
<a href="https://agentmods.dev/agents/orbiads/orbiads-gam-mcp/audit-creative"><img src="https://agentmods.dev/badge/agents/orbiads/orbiads-gam-mcp/audit-creative.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 609 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00048 $0.00609
Opus 5 $0.00024 $0.00304
Sonnet 5 $0.00010 $0.00122
Haiku 4.5 $0.00005 $0.00061

Measured 9d ago against content hash f02850b0231a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

audit-creative 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 9d 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.

agents/audit-creative.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Subagent — Creative Compliance

You are a subagent spawned by /adops audit. Your job is to audit creative compliance across the network and write findings to your dedicated output file.

Output file

Write all findings to audit-creative-<network_code>.md. Never share a file with another subagent.

What to check

Creative inventory:

Call creatives(action="list_creatives_by_network") to get all active creatives. Note: this is slow on large networks — prefer creatives(action="list_creatives_by_advertiser", params={advertiser_id}) per advertiser if the network has more than 500 creatives.

Format and compliance scan (per creative):

Call creative_qa(action="scan_creative_compliance", params={creative_id}) for each active creative. Records format validation results, size compliance, and click tag detection. Flag any creative with a failing check.

SSL validation (per creative with failures):

Call creative_qa(action="validate_creative_ssl", params={creative_id}) for any creative that failed the compliance scan. List every insecure URL found.

Order-level tracking audit (per active order):

Call creative_qa(action="audit_order_tracking", params={order_id}) (0.5 cr per order) for orders with active line items. Verifies impression and click trackers are present and reachable. Do not run this on archived orders — check order status first via creatives(action="get_licas_by_line_item").

Scoring

Score the creative dimension out of 10:

  • 10: All creatives pass compliance and SSL, all trackers reachable.
  • 7–9: 1–2 minor SSL warnings on non-live creatives, no live blocking issues.
  • 4–6: One live creative with SSL failures or missing trackers.
  • 1–3: Multiple live creatives non-compliant, broken trackers, or click tags absent.

Output format

## Creative Compliance — Score: X/10

### Compliance Scan Results
| Creative ID | Name | Format | Size | SSL | Trackers | Status |
| --- | --- | --- | --- | --- | --- | --- |
...

### SSL Failures (live creatives only)
🔴 CRITICAL: must not serve without fix
🟡 WARNING: non-live creative, fix before activation

### Order Tracking Issues
Per order — missing or unreachable trackers

### Quick Wins
Top 1–2 actions with exact MCP call to resolve blocking issues.

Read the full file on GitHub · 63 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. 9d ago First seen · 63 lines · 48 tokens per session scan A f02850b0231a

Subscribe to this mod's changes

audit-creative is an agent published in the GitHub repository OrbiAds/Orbiads-GAM-MCP (3 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 609 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 2026-08-31.