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/commands/orbiads/orbiads-gam-mcp/adops-audit)<a href="https://agentmods.dev/commands/orbiads/orbiads-gam-mcp/adops-audit"><img src="https://agentmods.dev/badge/commands/orbiads/orbiads-gam-mcp/adops-audit/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/commands/orbiads/orbiads-gam-mcp/adops-audit"><img src="https://agentmods.dev/badge/commands/orbiads/orbiads-gam-mcp/adops-audit.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 | $0.00030 | $0.01280 |
| Opus 5 | $0.00015 | $0.00640 |
| Sonnet 5 | $0.00006 | $0.00256 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
adops-audit 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 12d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GAM Account Audit
Always start by confirming the tenant: call get_my_tenant_id. All audit operations are read-only and cost 0 credits unless noted.
Dimensions
Parse $ARGUMENTS to decide which dimensions to run.
| Dimension | Condition | Primary tool |
|---|---|---|
delivery |
Always | reporting(action="check_delivery_status") + reporting(action="check_underdelivery_alerts") (0.25 cr) |
inventory |
Always | inventory(action="audit_inventory") + audit_skill(action="hygiene_check") |
security |
If security or all |
audit_skill(action="standards_baseline", params={framework}) |
creative |
If creative or all and line items > 0 |
creative_qa(action="scan_creative_compliance") + creative_qa(action="audit_order_tracking") (0.5 cr) |
billing |
If billing or all |
reporting(action="generate_billing_report") (0.5 cr) + reporting(action="check_budget_alerts") (0.25 cr) |
Default (no argument): run all dimensions.
For --framework, pass to audit_skill(action="standards_baseline", params={framework}). The accepted framework identifiers are exactly (any other value → VALIDATION_ERROR):
orbiads_baseline(default) — 12 checks. ✅ Implemented.iso27001_adops— ISO 27001 ad-ops subset, 8 controls. ✅ Implemented.nist_csf_subset— NIST CSF subset, 8 controls. ✅ Implemented.iab_anti_tampering— declared but not implemented: it returnsNOT_IMPLEMENTED(advertiser-side anti-tampering, inapplicable to a publisher-side GAM audit). Do not offer it as a working option.
Use the full identifier (iso27001_adops, not iso27001) — the short names are rejected at validation.
Running the audit
Probe line item count first via reporting(action="check_delivery_status"). Then spawn each applicable subagent in parallel via the Task tool with context: fork. Each subagent writes to its own output file — never share a file between subagents.
Output file naming: audit-<dimension>-<network_code>.md
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.
- 12d ago First seen · 77 lines · 0 tokens per session scan A 15f669572cac
adops-audit is a command published in the GitHub repository OrbiAds/Orbiads-GAM-MCP (3 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,280 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
verify-pr
Verify a PR's frontend changes through browser automation.
explore
Explore a web page using browser automation.
record
Record browser actions into a test definition.
test-init
Initialize qa-use test directory with example test.
test-run
Run E2E tests with qa-use CLI.
context-resume
Call the context MCP tool with action: "resume", project: "$ARGUMENTS" (if no argument given, infer the project name from the current working directory name), and rootPath: " ".