Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/zpoint/vibe-sellernpx agentmods add skills/zpoint/vibe-seller/noon-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/zpoint/vibe-seller/noon-ads)<a href="https://agentmods.dev/skills/zpoint/vibe-seller/noon-ads"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/noon-ads/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/zpoint/vibe-seller/noon-ads"><img src="https://agentmods.dev/badge/skills/zpoint/vibe-seller/noon-ads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 361 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00089 | $0.05013 |
| Opus 5 | $0.00044 | $0.02507 |
| Sonnet 5 | $0.00018 | $0.01003 |
| Haiku 4.5 | $0.00009 | $0.00501 |
Grade A, and why
noon-ads 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 11d 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 — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Noon — Ad Manager
PREREQUISITE: Read
../noon-shared/SKILL.mdfor login, page structure, and common patterns.
Mechanics for noon Ad Manager. The actual thinking — when to create / tune / kill a campaign, how to research keywords — lives in the three reference files (see § 11).
URL: https://admanager.noon.partners/en-{cc}/home?mpCode=noon&project=PRJ{project_id}
Left nav (ul role=menu): Campaigns, Budget, Billing,
Vantage (Beta), Settings. Country switcher at bottom.
1. Campaigns Overview Metrics
Top-level KPI cards:
| Metric | Formula / Notes |
|---|---|
| ROAS | Return on Ad Spend = Revenue / Spends |
| Revenue | Total ad-attributed revenue |
| Spends | Total ad spend |
| eCPC | Effective Cost Per Click |
| CTR | Click-Through Rate = Clicks / Views |
| Orders | Ad-attributed orders |
| Clicks | Total clicks on ads |
| Views | Total ad impressions |
| ATC | Add To Cart count |
| CvR | Conversion Rate (shown on campaign detail) |
A time-series performance chart below lets you toggle any metric.
2. Campaign List Filters
- Status (Active/Paused/etc.)
- Ad Type
- Date range
Columns: Performance (chart), ROAS, Revenue, Spends, eCPC, CTR, Orders, Campaign Details, Status, Budget.
3. Campaign Detail Page
URL: admanager.noon.partners/en-{cc}/campaign/details/{campaign_id}?mpCode=noon&project=PRJ{project_id}
Campaign ID format: C_{alphanumeric} (10 alphanumerics after the
underscore, e.g. C_XXXXXXXXXX).
Campaign ID extraction from the campaigns list (IDs are in
<a href> attributes, not visible text):
browser-use eval "var links = document.querySelectorAll('a[href*=\"/campaign/details/\"]'); var data = []; links.forEach(function(l) { var m = l.href.match(/\/campaign\/details\/([^?]+)/); if (m) data.push({name: l.textContent.trim(), id: m[1]}); }); JSON.stringify(data);"
⚠️ The campaign list is PAGINATED (~15 per page) — that eval only returns the CURRENT page. The footer reads
Showing 15 items per pageand a pager (1 2 3 4 5 →) sits bottom-right. A single eval captures ~15 campaigns; an account with 70 campaigns across 5 pages will be silently under-reported by ~80% if you stop at page 1. This has produced a real audit that reported "12 active campaigns (all manual targeting)" for a noon account that actually had ~70 campaigns across 5 pages, including Auto-targeting and Product-Ad campaigns the page-1-only read never saw.Phase 1 (Discover) MUST enumerate every page before concluding the campaign set:
- Read the pager to learn the last page number, then page through all of them, unioning campaign IDs into one set. The pager is an Ant Design component — click the explicit page-number anchor
li.ant-pagination-item-N a(verified reliable 2026-06-08); the generic next-chevron snippet below is an unreliable fallback (the/next|›|→/match returnsno-nexton this paginator):Re-extract# RELIABLE: jump to each page by its number, 1..last browser-use eval "var a=document.querySelector('li.ant-pagination-item-2 a'); if(a){a.click(); 'page-2';} else 'no-page-2';" # how many pages exist: browser-use eval "JSON.stringify([...document.querySelectorAll('li.ant-pagination-item')].map(function(li){return li.getAttribute('title')||li.textContent.trim();}));" # fallback chevron (often fails on Ant Design — prefer the anchor): # browser-use eval "var b=[...document.querySelectorAll('button,a,[role=button]')].find(function(e){return /next|›|→|>/.test(e.getAttribute('aria-label')||e.textContent||'') && !e.disabled;}); if(b){b.click(); 'clicked-next';} else 'no-next';"a[href*="/campaign/details/"]after each page and merge into a de-duped set (IDs repeat if you re-read the same page).- Establish the true total before trusting any count: the last pager number × page-size (minus the short last page) is your completeness target. If the distinct campaign-id count you collected is less than
(last_page − 1) × 15, you have NOT read every page — keep going. Many noon list footers also expose a page-size selector; bumping it (e.g. 15 → 100) collapses the account to a single page and is the most reliable read when available.- Only after the union is complete (count stable, all pages visited) do you have the manifest. Treat a single-page read as a spot-check, never as the full campaign set. The same caveat applies per country — re-paginate after every country switch.
What ships with it
3 files 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.
- 11d ago First seen · 424 lines · 89 tokens per session scan A 5502a63dda31
noon-ads is a skill published in the GitHub repository zpoint/vibe-seller (66 stars, last pushed 3d ago), licensed Apache-2.0. It adds 89 tokens to every session and 5,013 once invoked, about $0.0004 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 2026-08-30.
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…