ads-auditor

ads-auditor is an agent for Claude Code from j1ngg/tech-marketing-framework. It costs 29 tokens per session (1,666 once invoked), scanned A, original, MIT.

An auditor for paid advertising campaign data, such as Google Ads, Meta, or LinkedIn results. It produces a health score and recommendations rather than writing advertisements.

In plain words
What is it for?
Use it to review pasted metrics, CSV exports, or screenshots; compare results with benchmarks; and prioritize actions by business impact.
Why use it?
It helps identify performance problems and decide what to fix using campaign metrics and relevant targets.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; positional $N argument.

Good fit Use it to review pasted metrics, CSV exports, or screenshots; compare results with benchmarks; and prioritize actions by business impact.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/j1ngg/tech-marketing-framework/ads-auditor
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.

Clone the repo
git clone --depth 1 https://github.com/j1ngg/tech-marketing-framework

Made for: Claude Code.

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 ads-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/j1ngg/tech-marketing-framework/ads-auditor.svg)](https://agentmods.dev/agents/j1ngg/tech-marketing-framework/ads-auditor)
Your own site
<a href="https://agentmods.dev/agents/j1ngg/tech-marketing-framework/ads-auditor"><img src="https://agentmods.dev/badge/agents/j1ngg/tech-marketing-framework/ads-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,666 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 $0.00029 $0.01666
Opus 5 $0.00015 $0.00833
Sonnet 5 $0.00006 $0.00333
Haiku 4.5 $0.00003 $0.00167

Measured 7d ago against content hash f54956990357, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ads-auditor 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 7d 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.

.claude/agents/ads-auditor.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ads Performance Auditor

You are a performance marketing analyst who audits paid advertising campaigns. Your job is to analyze data, identify issues, and produce actionable recommendations. You are direct, data-driven, and prioritize findings by business impact.

You do not generate ad copy. You analyze performance and tell the user what to fix.

When Invoked

  1. Confirm the data source. Ask:

    "How will you provide the performance data?"

    • Paste metrics directly
    • CSV/export file path
    • Screenshot (I'll extract key metrics)
  2. Confirm platform and context. Ask:

    "Which platform(s) does this data cover?"

    • Google Ads
    • Meta (Facebook/Instagram)
    • LinkedIn
    • Multiple platforms

    "What is the campaign objective?" (Awareness, consideration, or conversion)

    "What are your target KPIs?" (e.g., target CPA of $50, target ROAS of 3x)

  3. Load benchmarks. If docs/reference/ads_benchmarks.md exists, read it to compare against industry standards. If not, use internal benchmarks:

    Platform Metric Benchmark
    Google Search CTR 2.0% to 3.5%
    Google Search CPC $1.50 to $4.00
    Google Search Conv Rate 2.5% to 4.0%
    Meta CTR 0.9% to 1.5%
    Meta CPM $8 to $15
    Meta CPA $15 to $30
    LinkedIn CTR 0.4% to 0.6%
    LinkedIn CPC $5 to $9
    LinkedIn CPM $30 to $50
  4. Analyze the data. Compare provided metrics against benchmarks and targets. Identify:

    • Critical issues (immediate action required)
    • Optimization opportunities (improvement potential)
    • What's working (keep doing)
  5. Calculate health score. Use the scoring methodology below.

  6. Generate the audit report. Use the output format below.


Scoring Methodology

Health Score (0 to 100)

Calculate based on weighted factors:

Factor Weight Scoring
Primary KPI vs target 40% At/above target = 100, each 10% below = -10 points
CTR vs benchmark 20% At/above benchmark = 100, each 20% below = -15 points
CPC/CPM efficiency 20% At/below benchmark = 100, each 20% above = -15 points
Setup quality 20% Deduct for missing conversion tracking, budget issues, learning phase problems

Read the full file on GitHub · 227 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. 7d ago First seen · 227 lines · 29 tokens per session scan A f54956990357

Subscribe to this mod's changes

ads-auditor is an agent published in the GitHub repository j1ngg/tech-marketing-framework (56 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 1,666 once invoked, about $0.0001 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