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-report)<a href="https://agentmods.dev/commands/orbiads/orbiads-gam-mcp/adops-report"><img src="https://agentmods.dev/badge/commands/orbiads/orbiads-gam-mcp/adops-report/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-report"><img src="https://agentmods.dev/badge/commands/orbiads/orbiads-gam-mcp/adops-report.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 | $0.01095 |
| Opus 5 | $0.00015 | $0.00548 |
| Sonnet 5 | $0.00006 | $0.00219 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
adops-report 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 10d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GAM Reporting
Always confirm the tenant first: get_my_tenant_id. Most operations are read-only. Credit costs are shown per action.
Note: The REST Interactive Reports API does not work on test network 45515589. Use the production network.
delivery [campaign-id]
reporting(action="check_delivery_status", params={job_id}) — free. Shows pacing %, impressions vs. goal, fill rate.
Then call reporting(action="check_underdelivery_alerts") — costs 0.25 cr — to surface active delivery anomalies. If pacing < 80%, suggest running /adops audit delivery.
run
Build a custom report interactively:
- Fetch available dimensions:
reporting(action="get_report_dimensions")— free. - Fetch available metrics:
reporting(action="get_report_metrics")— free. - Fetch valid date range options:
reporting(action="get_report_date_ranges")— free. - Submit the report:
reporting(action="run_custom_report", params={dimensions, metrics, date_range, filters})— costs 0.5 cr. - Poll until complete:
reporting(action="get_report_result", params={execution_id})— free. - Render the first 20 rows inline. Offer to export the rest.
For a saved GAM report: reporting(action="run_gam_report", params={report_id}) — free. Fetch existing reports first via reporting(action="list_gam_reports").
For Google Analytics data: reporting(action="run_ga_report", params={metrics, dimensions, date_range}) — costs 0.5 cr. Fetch GA dimensions/metrics via reporting(action="get_ga_dimensions") and reporting(action="get_ga_metrics").
export <execution-id>
reporting(action="export_report_csv", params={execution_id}) — costs 0.5 cr. Confirm the row count after export.
templates [list|save|run <id>]
list — reporting(action="list_report_templates") — free.
save — Build template params from the user's input, then reporting(action="save_report_template", params={name, dimensions, metrics, date_range, filters}) — free.
run <id> — reporting(action="run_report_from_template", params={template_id}) — costs 0.5 cr. Follow the same poll/render flow as run above.
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.
- 10d ago First seen · 80 lines · 30 tokens per session scan A 0c7508555c3f
adops-report 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 1,095 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
verify-pr
Verify a PR's frontend changes through browser automation.
record
Record browser actions into a test definition.
explore
Explore a web page using browser automation.
test-init
Initialize qa-use test directory with example test.
test-run
Run E2E tests with qa-use CLI.
context-resume
Call the context MCP tool with action: "resume", project: "$ARGUMENTS" (if no argument given, infer the project name from the current working directory name), and rootPath: " ".