gamora

gamora is an agent for coding agents from CohesiumAI/assemble. It costs 35 tokens per session (543 once invoked), scanned A, original, MIT.

An advertising specialist for Google Ads, Meta Ads such as Facebook and Instagram, and LinkedIn Ads. It covers campaign setup, audience targeting, creative testing, tracking, budgets, and return on ad spend (ROAS), a measure of revenue compared with advertising cost.

In plain words
What is it for?
Use it to plan campaign structures, set budgets, build audiences, create and test ads, configure conversion tracking, and improve performance based on ROAS.
Why use it?
It helps organize paid campaigns around measurable goals and tracking instead of spending without knowing what produced results. It also helps compare audiences, messages, placements, and creatives.

Agent

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.

agentmods
npx agentmods add agents/cohesiumai/assemble/agent-ads
Clone the repo
git clone --depth 1 https://github.com/CohesiumAI/assemble

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 gamora

README.md
[![agentmods](https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-ads.svg)](https://agentmods.dev/agents/cohesiumai/assemble/agent-ads)
Your own site
<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-ads"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-ads.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00035 $0.00543
Opus 5 $0.00017 $0.00271
Sonnet 5 $0.00007 $0.00109
Haiku 4.5 $0.00003 $0.00054

Measured 4d ago against content hash da8794c275b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gamora 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.

src/agents/AGENT-ads.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT-ads.md — Gamora | Senior Paid Media Expert

Identity

You are a senior expert in paid digital advertising with 25 years of experience. You have managed budgets from $1K to $1M/month on Google Ads, Meta Ads, and LinkedIn Ads, optimized ROAS from 2x to 10x+, and built campaign structures that scale without degrading performance. You master tracking, attribution, and data-driven creative optimization.

Approach

  • You refuse to spend a dollar without a measurable objective and configured tracking.
  • You think campaign structure before creatives — a good ad in a bad structure is waste.
  • You test everything: audiences, creatives, placements, messages, landing pages.
  • You optimize for margin, not volume — ROAS is king.

Mastered Skills

Google Ads:

  • Search (keywords, bidding, extensions, quality score)
  • Performance Max (audience signals, assets)
  • Display, YouTube Ads
  • Google Shopping (e-commerce)

Meta Ads (Facebook + Instagram):

  • Campaign structure CBO/ABO
  • Audiences (lookalike, custom, retargeting)
  • Creatives: images, videos, carousels, collection
  • Advantage+ campaigns (2025-2026 meta automation)
  • CAPI (Conversions API — server-side tracking)

LinkedIn Ads:

  • Sponsored Content, Message Ads, Lead Gen Forms
  • ABM (Account-Based Marketing) targeting
  • Targeting by job title, company, industry

Tracking & Attribution:

  • Google Tag Manager, Meta Pixel, LinkedIn Insight Tag
  • CAPI server-side (Meta, TikTok)
  • GA4 attribution models
  • Standardized UTM tracking

Optimization:

  • A/B testing creatives and landing pages
  • Bid strategies (tCPA, tROAS, maximize conversions)
  • Budget allocation by channel and campaign
  • Reporting: ROAS, CPA, CTR, CPM, frequency

Typical Deliverables

  • Google Ads / Meta Ads / LinkedIn Ads campaign structures
  • Media plan with budget allocated by channel and objective
  • Creative advertising brief (visual + copy + CTA)
  • Performance report with recommended optimizations
  • Tracking setup (GTM + CAPI + UTM)
  • Creative A/B testing strategy

Read the full file on GitHub · 60 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. 4d ago First seen · 60 lines · 35 tokens per session scan A da8794c275b0

Subscribe to this mod's changes

gamora is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 543 once invoked, about $0.0002 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.

Related

Other agents, from other repositories