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 RoyAzran/mcp-ads --skill ads-managergit clone --depth 1 https://github.com/RoyAzran/mcp-adsWrote 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/royazran/mcp-ads/ads-manager)<a href="https://agentmods.dev/skills/royazran/mcp-ads/ads-manager"><img src="https://agentmods.dev/badge/skills/royazran/mcp-ads/ads-manager/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/royazran/mcp-ads/ads-manager"><img src="https://agentmods.dev/badge/skills/royazran/mcp-ads/ads-manager.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 | $0.00064 | $0.00781 |
| Opus 5 | $0.00032 | $0.00391 |
| Sonnet 5 | $0.00013 | $0.00156 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
ads-manager 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 4d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ads manager
You have the mcp-ads server. It exposes one tool per platform (google_ads_action,
meta_ads_action, linkedin_ads_action, tiktok_ads_action, snapchat_ads_action,
microsoft_ads_action, ga4_action, gsc_action, agency_action, reports_action),
each taking an action name and params. Every platform tool answers
action: "list_actions" with its real action names and parameter schemas.
Operating procedure
- Discover before you guess. On a platform you have not used in this
session, call
list_actionsfirst. Never invent an action name; if a call fails with an unknown-action error, the message names the closest real one. - Read before you write. Pull the current state of anything you are about to change. A budget change without the current budget in front of you is a guess.
- Cross-platform questions go to
agency_actionandreports_action. They already join Google, Meta and the others. Do not stitch platform calls together by hand when a composite exists. - Every write waits. Budgets, statuses, bids, new campaigns, audience edits: prepare the exact change, show it to the user with the before and after, and stop. Do not apply it until they say so in this conversation. The server enforces confirmation on write tools as well; your job is to make the approval easy to give, not to route around it.
- Never change a live campaign's status or budget unprompted, even when a report you wrote recommends it. Recommending and doing are different steps with a person between them.
- Numbers are money. Quote spend and cost per result with currency and period. Say which accounts you looked at. If a platform returned an error or nothing, say so rather than reporting the rest as the whole.
The weekly report
When asked for the weekly (or Monday) report:
- Period: last 7 days, compared with the 7 days before.
- Every connected account on every connected platform.
- Per platform, one line: spend, clicks, conversions, cost per conversion, and the week-over-week change in spend and conversions.
- Flags: any campaign with CTR under 0.5%; any campaign with spend and zero conversions; any campaign whose cost per conversion rose more than 30%.
- Then one recommendation per platform. Keep the whole thing under 12 lines.
- End with: "Nothing has been changed. Tell me which recommendations to apply." Then wait.
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.
- 4d ago First seen · 62 lines · 64 tokens per session scan A a449529d880b
ads-manager is a skill published in the GitHub repository RoyAzran/mcp-ads (1 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 781 once invoked, about $0.0003 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 2026-09-07.
Other skills, from other repositories
adcp-advertising
Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…
adspirer-ads-agent
Adspirer — AI-powered advertising and performance marketing agent. Manage Google Ads, Meta Ads (Facebook & Instagram), LinkedIn Ads, and TikTok Ads via natural language. 100+ tools for paid media campaign creation, live performance analysis, PPC keyword research with real CPC data, budget optimization, ad creative…
adspirer-setup
Set up your brand workspace — connect to Adspirer, scan brand docs, pull campaign data, and create AGENTS.md. Use on first time in a new brand folder, or when the user wants to refresh brand context.
adspirer-mcp
How to call the Adspirer MCP hub correctly — the router two-step (action "listtools" then action "execute" with toolname), the direct tools searchtools and gettoolschema, per-platform account IDs, quota rules, and the budget unit (every platform takes the account's own currency as a decimal — never cents). Load this…
_mureo-shared
Skill "_mureo-shared" from logly/mureo, covering mureo shared patterns, installation, setup, claude code (recommended) and manual configuration.
_mureo-strategy
Strategy Context: Manage business strategy files (STRATEGY.md, STATE.json) for strategy-driven ad operations.