ad-campaign

ad-campaign is a skill for Claude Code, Codex from canvora/canvora-mcp. It costs 57 tokens per session (1,334 once invoked), scanned A, original, MIT.

A tool for producing sets of paid advertising designs for platforms such as Meta, Instagram, LinkedIn, and Google Display.

In plain words
What is it for?
It helps create square, portrait, landscape, banner, and Google Display creatives with a consistent look across a campaign.
Why use it?
It covers the different image shapes needed for feeds, stories, reels, link ads, and display placements, while providing variants for testing.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit It helps create square, portrait, landscape, banner, and Google Display creatives with a consistent look across a campaign.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/canvora/canvora-mcp/ad-campaign
Install

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.

Any agent
npx skills add canvora/canvora-mcp --skill ad-campaign
Clone the repo
git clone --depth 1 https://github.com/canvora/canvora-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for ad-campaign

README.md
[![agentmods](https://agentmods.dev/badge/skills/canvora/canvora-mcp/ad-campaign/github.svg)](https://agentmods.dev/skills/canvora/canvora-mcp/ad-campaign)
Your own site
<a href="https://agentmods.dev/skills/canvora/canvora-mcp/ad-campaign"><img src="https://agentmods.dev/badge/skills/canvora/canvora-mcp/ad-campaign/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.

agentmods 80×15 button for ad-campaign

Your own site · 80×15
<a href="https://agentmods.dev/skills/canvora/canvora-mcp/ad-campaign"><img src="https://agentmods.dev/badge/skills/canvora/canvora-mcp/ad-campaign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,334 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.01334
Opus 5 $0.00028 $0.00667
Sonnet 5 $0.00011 $0.00267
Haiku 4.5 $0.00006 $0.00133

Measured 10d ago against content hash d35da4ed443d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ad-campaign 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.

skills/ad-campaign/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ad creative sets

Ads fail on placement coverage and on having only one creative to test. Canvora fixes both cheaply: every placement from one source in a single call, then variants from the winner. Setup and credits: see the canvora skill.

Placement map

Format Size Placement
ad_square 1:1 feed (Meta, LinkedIn, the safe default)
ad_portrait 9:16 stories, reels, vertical video slots
ad_landscape 16:9 1200×628 link ads, in-stream, LinkedIn sponsored
ad_banner 21:9 728×90 classic leaderboard display
google_display 1200×628 Google Display Network

Full coverage = ad_square,ad_portrait,ad_landscape — three placements, 30 credits, one consistent look. Add ad_banner/google_display only if they actually run display.

Ads are 10 credits per creative. Say the total in the same message as the run — announce it, don't ask permission; if you decided the number of angles yourself, confirm that number. A campaign is several sequential calls, so sum the whole plan and run canvora credits --json once before you start: running dry halfway leaves a half-covered campaign with the earlier calls already paid for. Any single call producing 3+ creatives should fire-and-poll rather than --wait — most harnesses kill a shell command at 120s while the generation carries on server-side, and re-running generate starts a second, separate job. See the canvora skill's "Long runs" section.

Intake

  1. What's being advertised? A product URL is the best input — it carries the offer, the proof and the brand voice. Otherwise the offer in one line.
  2. Where does it run? Meta/IG → square + portrait. LinkedIn → square + landscape. Google Display → google_display + ad_banner. Unsure → the three-format set.
  3. Brand kit--brand + --logo. Ads without the mark waste the spend.
  4. The offer/CTA — "20% off first order", "Book a demo". Put it in the brief and pass --cta.

Read the full file on GitHub · 117 lines

Changes

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.

  1. 10d ago First seen · 117 lines · 57 tokens per session scan A d35da4ed443d

Subscribe to this mod's changes

ad-campaign is a skill published in the GitHub repository canvora/canvora-mcp (0 stars, last pushed 29d ago), licensed MIT. It adds 57 tokens to every session and 1,334 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.