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 shinypebble/openai-ads-mcp --skill openai-ads-optimizergit clone --depth 1 https://github.com/shinypebble/openai-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/shinypebble/openai-ads-mcp/openai-ads-optimizer)<a href="https://agentmods.dev/skills/shinypebble/openai-ads-mcp/openai-ads-optimizer"><img src="https://agentmods.dev/badge/skills/shinypebble/openai-ads-mcp/openai-ads-optimizer/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/shinypebble/openai-ads-mcp/openai-ads-optimizer"><img src="https://agentmods.dev/badge/skills/shinypebble/openai-ads-mcp/openai-ads-optimizer.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 | $0.00101 | $0.01391 |
| Opus 5 | $0.00051 | $0.00696 |
| Sonnet 5 | $0.00020 | $0.00278 |
| Haiku 4.5 | $0.00010 | $0.00139 |
Grade A, and why
openai-ads-optimizer 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenAI Ads Optimizer
You are optimizing a single OpenAI Ads advertiser account via the openai-ads MCP server.
This skill explains how the account is structured, which tool to reach for, and the rules
for writing good ad copy.
Mental model
- One account per server. The API key identifies a single ad account; there is no account switching.
- Hierarchy:
AdAccount → Campaign → AdGroup → Ad. An Ad holds the creative (title/body/image/landing URL) and a moderationreview_status. - Two data sources for performance: insights (impressions/clicks/spend, with daily breakdown) and conversions (a separate aggregate, no daily trend). The tools join them for you.
- No global ad list. You cannot "list all ads." Ad groups are listed per campaign and
ads per ad group.
account_overviewwalks this for you — use it instead of trying to enumerate ads yourself.
Always start here
account_health— confirms the key works and reportscurrency,timezone, andread_only. Ifread_onlyis true, write tools are not available this session: produce a recommended-changes report instead of attempting writes, and tell the user to setREAD_ONLY=falseto execute.account_overview— the campaign → ad group → ad tree with statuses and counts. Use it to orient before drilling in.
Workflow: find and disable dead ads
ad_performance(since, until)over an inclusiveYYYY-MM-DDwindow (default to the last 7, 14, or 30 days). Each row has derived CTR/CPC/CPM, joined conversions and cost-per-conversion, and aflag:dead— enough impressions but ~no clicks. Strong candidate to pause/archive.underperforming— very low CTR. Candidate to rewrite or pause.ok— leave it, or it lacks enough impressions to judge. Rows are returned worst-first. Tunemin_impressions,dead_max_clicks, andunderperf_max_ctrif the defaults don't fit the account's volume.
- Act:
pause_ads(ad_ids)(reversible) for things to revisit;archive_ads(ad_ids, confirm=true)only when you're certain — archiving is irreversible and removes the ad from list views. - Gotcha: pausing a campaign or ad group does not change its children's status — they
stay
activebut stop serving. If an ad looks active but isn't spending, callget_ad(ad_id)and read itsserving_issues(only by-id reads include them).
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 · 101 lines · 101 tokens per session scan A 02518da7a466
openai-ads-optimizer is a skill published in the GitHub repository shinypebble/openai-ads-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 101 tokens to every session and 1,391 once invoked, about $0.0005 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…