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-campaign)<a href="https://agentmods.dev/commands/orbiads/orbiads-gam-mcp/adops-campaign"><img src="https://agentmods.dev/badge/commands/orbiads/orbiads-gam-mcp/adops-campaign/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-campaign"><img src="https://agentmods.dev/badge/commands/orbiads/orbiads-gam-mcp/adops-campaign.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 | $0.01713 |
| Opus 5 | $0.00018 | $0.00856 |
| Sonnet 5 | $0.00007 | $0.00343 |
| Haiku 4.5 | $0.00004 | $0.00171 |
Grade A, and why
adops-campaign 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 11d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GAM Campaign Lifecycle
Always start by confirming the tenant: call get_my_tenant_id. If unauthenticated, stop and ask the user to run orbiads auth login.
read
Call campaign(action="read", params={campaign_id}).
This returns a live CampaignRecap: order, groups, line items, LICAs, creatives, and targeting assembled from GAM. It is free and performs zero GAM writes.
Use this recap as the source of truth before edit-intents, diagnostics, or resume work. It reflects GAM live state, not a Firestore mirror or previous LLM context that may have drifted.
dry-run
Call campaign(action="dry_run", params={campaign_id}) or campaign(action="dry_run", params={job_id}).
The server returns a signed ExecutionPlan:
{
operation,
resourceType: "campaign",
preview,
mutations[],
risks[],
warnings[],
estimatedCost,
confirmationToken,
expiresIn: 300
}
This step is free and performs zero GAM or Firestore writes. The confirmationToken produced here is consumed by campaign(action="deploy").
Error handling:
CONFIRMATION_REQUIRED: no token was supplied for execute; re-rundry_run.PAYLOAD_MISMATCH: the payload drifted between dry-run and deploy; re-rundry_run.TOKEN_EXPIRED: the token is older than 300 seconds; re-rundry_run.
plan-deployment
Call campaign(action="plan_deployment", params={preset, ...}).
Available presets: display_banner, video_vast, video_hosted, audio_vast, audio_hosted, custom_spec. Pass product_id when an ADCP Product should prefill placements, pricing, and formats.
The server returns a signed ExecutionPlan with dry_run=true implied. It is free, and the resulting token is consumed by campaign(action="deploy_media").
deploy-media
Call campaign(action="deploy_media", params={confirmation_token}).
This executes through the unified CampaignPipeline.deploy saga. It costs credits using the same grid as deploy, and it requires a confirmation_token from plan_deployment or dry_run.
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.
- 11d ago First seen · 149 lines · 37 tokens per session scan A 6156ac956308
adops-campaign 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 1,713 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: " ".