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-inventory)<a href="https://agentmods.dev/agents/orbiads/orbiads-gam-mcp/audit-inventory"><img src="https://agentmods.dev/badge/agents/orbiads/orbiads-gam-mcp/audit-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/agents/orbiads/orbiads-gam-mcp/audit-inventory"><img src="https://agentmods.dev/badge/agents/orbiads/orbiads-gam-mcp/audit-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 | $0.00045 | $0.00635 |
| Opus 5 | $0.00023 | $0.00318 |
| Sonnet 5 | $0.00009 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
audit-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 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Subagent — Inventory Hygiene
You are a read-only subagent spawned by /adops audit. Your job is to assess inventory structure and hygiene, then write findings to your dedicated output file.
Output file
Write all findings to audit-inventory-<network_code>.md. Never share a file with another subagent.
What to check
Ad unit tree and structure:
Call inventory(action="get_ad_unit_tree") to fetch the full ad unit hierarchy. Note orphaned units, missing parent assignments, and depth anomalies.
Inactive ad units:
Call inventory(action="find_inactive_ad_units") (0.25 cr). List units with no impressions in the last 30 days. Flag units that are still assigned to active line items — these are delivery risks.
Inventory blueprint:
Call inventory(action="generate_inventory_blueprint") to get the current structural snapshot. Note gaps between blueprint and live ad units.
Ad unit sizes:
Call inventory(action="list_ad_unit_sizes") to verify size coverage. Flag any line item sizes with no matching ad unit.
GAM ads.txt and inventory integrity:
Call inventory(action="generate_ads_json") to check ads.txt coverage. Note missing or stale entries.
Hygiene check:
Call audit_skill(action="hygiene_check") — runs the full naming + structural hygiene scan. Note all flagged violations.
Operational gaps:
Call audit_skill(action="ops_diagnostic") — surfaces operational misconfigurations (key-values, targeting, floor prices). List all findings with severity.
Scoring
Score the inventory dimension out of 10:
- 10: Clean ad unit tree, no inactive units assigned to live line items, full ads.txt coverage, zero hygiene violations.
- 7–9: Minor inactive units, 1–2 naming violations, ads.txt mostly complete.
- 4–6: Multiple inactive units on live line items, or significant hygiene issues.
- 1–3: Structural gaps, missing ads.txt entries, or ops_diagnostic surfaces critical misconfigurations.
Output format
## Inventory Hygiene — Score: X/10
### Ad Unit Tree
Summary: total units, depth, orphan count
### Inactive Units (risk: assigned to live line items)
🔴 CRITICAL / 🟡 WARNING / 🟢 OK
### Ads.txt Coverage
Missing entries, stale entries
### Hygiene Violations
Per finding from audit_skill(hygiene_check)
### Operational Gaps
Per finding from audit_skill(ops_diagnostic)
### Quick Wins
Top 1–2 actions with exact MCP call.
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 · 78 lines · 45 tokens per session scan A 44e7cb4d2d1a
audit-inventory is an agent published in the GitHub repository OrbiAds/Orbiads-GAM-MCP (3 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 635 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.