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-inventory)<a href="https://agentmods.dev/commands/orbiads/orbiads-gam-mcp/adops-inventory"><img src="https://agentmods.dev/badge/commands/orbiads/orbiads-gam-mcp/adops-inventory/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-inventory"><img src="https://agentmods.dev/badge/commands/orbiads/orbiads-gam-mcp/adops-inventory.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 | $0.00037 | $0.01039 |
| Opus 5 | $0.00018 | $0.00519 |
| Sonnet 5 | $0.00007 | $0.00208 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
adops-inventory 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GAM Inventory, Placements, and Targeting
Always confirm the tenant first: get_my_tenant_id. All read operations are free.
Load the orbiads orchestrator skill on first use; this command then delegates to the inventory consolidated skill for detailed action guidance.
list-units [parent-id]
targeting(action="list_ad_units") — returns the full ad unit tree. Pass parent_ad_unit_id to scope to a subtree. For targeted lookup: targeting(action="search_ad_units", params={query}). For bulk fetch by IDs: inventory(action="get_ad_units_by_ids", params={ids: [...]}).
Always list before any placement or targeting write — the business scope must be frozen first.
list-placements [name-filter]
placements(action="list_placements") — returns all placements with their constituent ad unit IDs.
Before creating or updating: read current state. Before proposing names or grouping changes, call settings(action="get_naming_conventions") and apply the returned pattern.
targeting
Reads (all free):
targeting(action="list_custom_targeting_keys")— all custom targeting keys.targeting(action="get_custom_targeting_values", params={key_id})— values for a key.targeting(action="get_available_countries")— country lookups.targeting(action="get_device_categories")— device families.targeting(action="get_browsers")/targeting(action="get_operating_systems")— browser/OS lists.targeting(action="get_content_labels")— Google content categories.
Writes (require confirmation_token from dry-run preview):
targeting(action="create_custom_targeting_key", params={name, display_name, type, dry_run: true})— preview first; then execute withconfirmation_token.targeting(action="create_custom_targeting_values", params={key_id, name, display_name, dry_run: true}).targeting(action="perform_custom_targeting_value_action", params={value_ids, action_type, dry_run: true})— surface impact before acting on values.
Validate Native/Fluid targeting compatibility with targeting(action="validate_fluid", params={ad_unit_id}).
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 · 78 lines · 37 tokens per session scan A 02e888ff79d6
adops-inventory is a command published in the GitHub repository OrbiAds/Orbiads-GAM-MCP (3 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 1,039 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: " ".