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.
npx skills add amekala/ads-mcp --skill adspirer-ads-manager-browsergit clone --depth 1 https://github.com/amekala/ads-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/skills/amekala/ads-mcp/adspirer-ads-manager-browser)<a href="https://agentmods.dev/skills/amekala/ads-mcp/adspirer-ads-manager-browser"><img src="https://agentmods.dev/badge/skills/amekala/ads-mcp/adspirer-ads-manager-browser/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/skills/amekala/ads-mcp/adspirer-ads-manager-browser"><img src="https://agentmods.dev/badge/skills/amekala/ads-mcp/adspirer-ads-manager-browser.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 | $0.00084 | $0.01973 |
| Opus 5.5 | $0.00034 | $0.00789 |
| Sonnet 5.5 | $0.00017 | $0.00395 |
| Haiku 4.5 | $0.00008 | $0.00197 |
Grade A, and why
adspirer-ads-manager-browser 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 18d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ads manager checks (read-only)
The browser looks. It never changes the account.
Advertisers send conversions in more than one way: a website tag, a Google tag through Tag Manager, a GA4 import, a server-side or offline upload (Conversions API, Data Manager, click imports), an app SDK, calls, or a platform-hosted lead form. Learn how this account tracks before you judge it. Never call tracking broken because a tag chip says Urgent, or because Data manager lists no source. Those signals apply only to actions that use that source. Some server-side setups are not fully visible in the UI. Say what you could not see.
Read the API at the same time
Follow adspirer-mcp.
get_connections_statusfor the accounts in scope. Skip accounts the user has marked out of scope.audit_conversion_trackingfor Google, Meta, and LinkedIn. Pass the platform and the account id as a string. With several Google Ads accounts connected it can ignorecustomer_idand still ask you to specify one. Retry that call once, then do this UI check and say the API audit was not available. See the error catalog inadspirer-mcp.- Other platforms:
list_toolson that platform's router for a pixel, conversion, or account-status read.get_tool_schemabefore you execute. - The audit looks back from today. If
freshness_statesays the cached data is old, or nothing has spent in the window, say that. It is not a broken tag.
Sign in first
Load adspirer-ads-manager-sign-in before the first check on a platform. That skill hands the
browser to the user, on any host that can do it, and confirms the account afterward. If a check
lands on a login, a 2FA prompt, or an account picker, stop and run it again. If this host has no
controllable browser, that skill says to fall back to the API. Don't start clicking, and never
ask for a password or a code.
Read-only, on every host
Never click save, apply, enable, accept, publish, verify, create, upload, or anything in billing or payment. Don't open edit panels or Manage dialogs. Read settings from summary rows and an action's detail or diagnostics page. If an edit panel opens by accident, close it with Cancel or the X. Don't dismiss alerts or apply recommendations.
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.
- 18d ago First seen · 91 lines · 84 tokens per session scan A 3656d1d85ee0
adspirer-ads-manager-browser is a skill published in the GitHub repository amekala/ads-mcp (106 stars, last pushed 4d ago), licensed MIT. It adds 84 tokens to every session and 1,973 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-20.
adspirer-ads-manager-browser compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| adspirer-ads-manager-browseramekala/ads-mcp | Skill | 106 | 4d ago | MIT | A | 84 | Claude Code |
| adspirer-ads-agentLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 141 | Claude Code, Codex |
| adcp-advertisingLeoYeAI/openclaw-master-skills | Skill | 2.2k | 6d ago | MIT | A | 103 | Claude Code, Codex |
| _mureo-sharedlogly/mureo | Skill | 63 | yesterday | Apache-2.0 | A | 22 | Claude Code |
| _mureo-strategylogly/mureo | Skill | 63 | yesterday | Apache-2.0 | A | 28 | Claude Code |
| _mureo-google-adslogly/mureo | Skill | 63 | yesterday | Apache-2.0 | A | 26 | Claude Code |
| _mureo-meta-adslogly/mureo | Skill | 63 | yesterday | Apache-2.0 | A | 27 | Claude Code |