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.
git clone --depth 1 https://github.com/j1ngg/tech-marketing-frameworkWrote 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/agents/j1ngg/tech-marketing-framework/ads-auditor)<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>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 | $0.00029 | $0.01666 |
| Opus 5 | $0.00015 | $0.00833 |
| Sonnet 5 | $0.00006 | $0.00333 |
| Haiku 4.5 | $0.00003 | $0.00167 |
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.
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
-
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)
-
Confirm platform and context. Ask:
"Which platform(s) does this data cover?"
- Google Ads
- Meta (Facebook/Instagram)
- 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)
-
Load benchmarks. If
docs/reference/ads_benchmarks.mdexists, 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 -
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)
-
Calculate health score. Use the scoring methodology below.
-
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 |
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.
- 7d ago First seen · 227 lines · 29 tokens per session scan A f54956990357
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.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.