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.
git clone --depth 1 https://github.com/OrbiAds/Orbiads-GAM-MCPWrote 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.
[](https://agentmods.dev/agents/orbiads/orbiads-gam-mcp/audit-creative)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 9d ago First seen · 63 lines · 48 tokens per session scan A f02850b0231a
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.
Other agents, from other repositories
browser-navigator
Autonomous browsing agent for multi-step web tasks. Use when: (1) User describes a browsing goal (e.g., "find the pricing page"), (2) Complex navigation requires multiple snapshot-action cycles, (3) AI-powered element discovery is needed.
browser-recorder
Record browser interactions and generate test definitions. Use when: (1) By feature-verify skill after exploration to generate test YAML, (2) By test-authoring skill for assisted test creation, (3) By user for "record this flow" requests.
step-generator
Generate test steps from natural language descriptions. Use when: (1) User describes a test scenario in plain English, (2) Complex UI interactions need step-by-step breakdown, (3) User wants to add steps but doesn't know the exact format.
test-analyzer
Deep analysis of E2E test failures and results. Use when: (1) A test has failed and needs root cause analysis, (2) User wants to understand why a step failed, (3) Complex multi-step failures need investigation.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.