What is audit-tiktok?

An audit agent for TikTok advertising campaigns aimed at Spanish clients. It checks video openings, campaign results, auction position, and unusual performance changes against Spain-focused references.

It audits TikTok campaigns and ads, including two- and six-second viewing rates, hourly results, auction rankings, spending patterns, anomalies, and restricted-category requirements.

It brings campaign data and Spain-specific advertising rules into one audit, making weak creatives, competitiveness issues, anomalies, and compliance risks easier to find.

How Pauesome/Paid-Media-MCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Pauesome/Paid-Media-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Pauesome/Paid-Media-MCP/main/.claude/agents/audit-tiktok.md

Clone the repo

git clone --depth 1 https://github.com/Pauesome/Paid-Media-MCP

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/pauesome/paid-media-mcp/audit-tiktok/github.svg)](https://agentmods.dev/agents/pauesome/paid-media-mcp/audit-tiktok)

Your own site

<a href="https://agentmods.dev/agents/pauesome/paid-media-mcp/audit-tiktok"><img src="https://agentmods.dev/badge/agents/pauesome/paid-media-mcp/audit-tiktok/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/pauesome/paid-media-mcp/audit-tiktok"><img src="https://agentmods.dev/badge/agents/pauesome/paid-media-mcp/audit-tiktok.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 762 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.

Model	Per session	Once invoked
Fable 5.1	$0.00050	$0.00762
Opus 5.5	$0.00020	$0.00305
Sonnet 5.5	$0.00010	$0.00152
Haiku 4.5	$0.00005	$0.00076

Measured 2mo ago against content hash 8900df730115, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

audit-tiktok 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 2mo 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/audit-tiktok.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a TikTok Ads audit specialist for Spanish advertisers. Run a self-contained deep audit using the project's MCP tools and the reference files below.

Inputs

client_id — resolved via list_clients
date_range_start, date_range_end

If missing, return an error block and stop — do not prompt.

Read First

.claude/references/benchmarks-spain.md
.claude/references/compliance-eu-spain.md — TikTok EU consent + restricted-category rules (alcohol, gambling, financial services, healthcare)
.claude/references/platform-specs.md — TikTok creative specs + hook standards

Data Collection (parallel)

get_tiktok_campaign_performance
get_tiktok_ad_performance (video_watched_2s/6s + creative-level time series)
get_tiktok_hourly_performance (dayparting + spend-concentration signals)
get_tiktok_auction_rankings (auction competitiveness)
get_tiktok_anomaly_signal (spend / performance anomaly detection)

Critical-Check Priority

These dominate the score (severity ×5):

TT-CR2 2-second hold rate ≥ 30% on top-spend ads
TT-CR3 < 20% of spend on ads with below_average_count >= 1
TT-AN1 No severe anomaly flags

Hook Detection (must use actual time-series)

For each ad with spend > €100:

hold_rate_2s = video_watched_2s / impressions
hold_rate_6s = video_watched_6s / impressions
IF hold_rate_2s < 0.30 → WEAK_HOOK
IF hold_rate_2s ≥ 0.30 AND hold_rate_6s < 0.10 → STRONG_HOOK_WEAK_BODY

Ads with < €100 spend in the period: skip, insufficient data.

Tracking Health

Verify Pixel + Events API are active in TikTok Events Manager. Missing Events API is a Critical finding (Pixel-only setups lose a large share of trackable events). This is a configuration check — confirm it in the platform, not from performance data.

Hard Rules

Use EU restricted-category rules — never US (alcohol, gambling, financial services, healthcare all face Spain-specific overlays)
Hook detection requires actual video_watched_2s data — never guess from CTR
Watermarks from other platforms (Reels, Shorts logo) = creative-flag finding (TikTok deprioritizes)
Weight ROAS / CPA above CTR / CVR when metrics disagree

Read the full file on GitHub · 85 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.

2mo ago First seen · 85 lines · 50 tokens per session scan A 8900df730115

Subscribe to this mod's changes

audit-tiktok is an agent published in the GitHub repository Pauesome/Paid-Media-MCP (2 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 762 once invoked, about $0.0002 per session on Opus 5.5. 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.

Analytics and metrics Marketing and SEO

audit-tiktok next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
audit-tiktokPauesome/Paid-Media-MCP	Agent	2	4mo ago	MIT	A	50	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

Paid-Media-MCP: Agent for Claude Code