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 kelpi-ai/meta-ads-skills --skill media-buyergit clone --depth 1 https://github.com/kelpi-ai/meta-ads-skillsWrote 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/kelpi-ai/meta-ads-skills/media-buyer)<a href="https://agentmods.dev/skills/kelpi-ai/meta-ads-skills/media-buyer"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/media-buyer/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/kelpi-ai/meta-ads-skills/media-buyer"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/media-buyer.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 | $0.00050 | $0.00510 |
| Opus 5 | $0.00025 | $0.00255 |
| Sonnet 5 | $0.00010 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
media-buyer 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 12d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media Buyer
Doctrine
Simple structure wins at small budgets: one campaign, one broad ad set, 3-5 genuinely different angles as separate ads. Fragmenting budget across many ad sets starves the algorithm of signal; low budgets get killed by too much structure, not too little. Targeting stays broad on purpose: post-Andromeda, the ad content is the targeting, and the $20/day test exists to find the angle that closes the loop before real money goes in.
When to use
- After Creative Director; you have approved ads and image hashes.
- Needs a Meta Ads MCP with write access. Everything is built paused; nothing spends until you publish.
Run it
Build me a test campaign, everything PAUSED until I review it:
1. Campaign: sales objective (or leads, if my offer is lead-gen), one campaign only.
2. Ad set: one, broad targeting (country + broad age range only, no interest stacks), $20/day budget.
3. Ads: one ad per approved angle, using these creatives: [IMAGE HASHES + COPY]. Do not blend angles.
4. Confirm the pixel/conversion event it optimizes toward, and flag if the pixel looks dead or misconfigured BEFORE anything else.
5. Show me the full structure as a table (campaign > ad set > ads with their angles) and wait. I will say "publish" when I have reviewed it.
Do not enable any Advantage+ creative enhancements. I want the creatives to run exactly as approved.
Guardrails
- Paused draft first, always. The human says "publish", the skill never assumes it.
- $20/day until an angle has proven itself with 2-3x target cost-per-result of spend. Scaling before signal is donating to Meta.
- One campaign. If you feel the urge to add a second ad set, you probably need a different angle instead.
- After publishing: hands off for a week. Daily edits reset learning. Reading daily is what the Daily Auditor is for.
Good output looks like
A paused campaign whose structure you can read in ten seconds, optimizing toward a verified conversion event, with each ad mapped to a named angle.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 37 lines · 50 tokens per session scan A 975df142b32c
media-buyer is a skill published in the GitHub repository kelpi-ai/meta-ads-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 510 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 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…