badi: Command for Claude Code

.claude/commands/ads-review.md

ads-review is a command for Claude Code from fatihkan/badi. It costs 0 tokens per session (1,194 once invoked), scanned A, original, MIT.

A planning command for Google Ads, an online advertising service where businesses pay to show ads for searches and other placements.

In plain words
What is it for?
Use it to plan keywords, Search and Performance Max campaign structures, responsive search ad text, conversion tracking, and ways to improve ad quality.
Why use it?
It turns a code project’s features and audience into an advertising plan based on the problems potential customers search for. It gives advice and a verdict, but does not spend money or run campaigns.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is fatihkan/badi's own configuration. It tells Claude Code how to work on badi itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything badi configures →

Part of the badi plugin — 81 skills, 86 commands, 30 agents, 7 hooks shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to fatihkan/badi. 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/fatihkan/badi/main/.claude/commands/ads-review.md
Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 81 skills, 86 commands, 30 agents, 7 hooks.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/fatihkan/badi/ads-review.svg)](https://agentmods.dev/commands/fatihkan/badi/ads-review)
Your own site
<a href="https://agentmods.dev/commands/fatihkan/badi/ads-review"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/ads-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,194 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 $0.00000 $0.01194
Opus 5 $0.00000 $0.00597
Sonnet 5 $0.00000 $0.00239
Haiku 4.5 $0.00000 $0.00119

Measured 8d ago against content hash aef46e24de24, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ads-review 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 8d 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/commands/ads-review.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Ads review command. Builds a project-aware Google Ads strategy — keyword universe, Search/PMax structure, RSA assets, Quality Score levers, conversion tracking — via the ads-strategist agent. Advisory only: plans and verdicts, no ad spend.

Required Tools

  • Read (memory, README, product context)
  • Grep / Glob (map the product surface: features, pricing, landing pages)
  • Bash (git log for product maturity signals)
  • WebSearch / WebFetch (keyword/competitor/policy research)
  • Agent (delegate to ads-strategist)

When to Use

When you want to advertise this project on Google Ads and need a strategy grounded in what the project actually is. Works like /ceo-review: context in, structured verdict out. For Meta use /meta-review; for producing creatives use the content-* commands. (Note: AdSense — showing ads on your own site — is a different need and out of scope here.)

Procedure

Step 1: Project Intake

  • Read memory.md, README, and any landing/marketing pages in the repo.
  • Derive: the searchable problem this product solves (Google Ads is intent capture — what would a buyer type?).

Step 2: Delegate to Ads Strategist (Google lens)

Launch the ads-strategist agent with the project context. Ask for:

  • Keyword universe: seed terms from the project's own vocabulary + research-expanded; match-type plan + negative list starter.
  • Campaign architecture: Search vs Performance Max trade-off for this product; ad-group theming. For PMax, use the 2026 campaign-level negative keywords to block branded/irrelevant queries and read the new channel + search-term-theme reports to catch Search bleed.
  • RSA asset coverage: headlines/descriptions angles derived from real features (hand production to content-*).
  • AI Max / Final URL expansion (2026): if enabled, verify tracking templates do not break expanded landing-page URLs (a known 404 risk) and that regulated-industry disclaimers are set; Call Ads creation was disabled in 2026 (existing ones keep serving until 2027), so if the plan leaned on them, rebuild as RSAs + call assets.
  • Quality Score levers: landing page ↔ ad relevance gaps found in the repo's actual pages.
  • Conversion tracking prerequisites (what counts as a conversion for this product; GA4/gtag plan), plus the privacy-durable layer to verify before launch:
    • Enhanced Conversions: supplement the gtag/GA4 tag with SHA-256-hashed first-party data (email required) matched to signed-in Google accounts. Google unified the old Web/Leads split into a single on/off toggle in 2026 and auto-migrated accounts — confirm the toggle is still ON and the Customer Data Terms are accepted (a migration can silently leave it off).
    • Offline Conversion Import: capture GCLID at click (or its iOS gbraid/wbraid fallbacks) and upload the CRM close with a conversion timestamp. The supported upload path moved in 2026 — new integrations use the Data Manager API; the legacy Google Ads API UploadClickConversions is blocked for integrations that were not already using it, so verify the pipeline still actually writes. Caveat: Enhanced Conversions for Leads does NOT match on gbraid/wbraid — iOS lead conversions stay unattributed, so size that traffic before promising volume.
    • Dedup: one unique transaction_id / order_id shared EXACTLY by the client tag and the upload, or conversions double-count.
    • Consent Mode v2 (ad_storage, analytics_storage, ad_user_data, ad_personalization), required for EEA/UK. In 2026 Google made Consent Mode — not Google Signals — the single control for EEA ad data reaching Google Ads (Google Signals now only governs signed-in association). There is no single "sole gate": a denied ad_storage (cookies), ad_user_data (sending user data, incl. Enhanced Conversions), OR ad_personalization (remarketing/personalization) each breaks a different piece. Verify the CMP passes correct per-user granted/denied for all four, not a blanket default — a universal denied silently zeroes out conversions and remarketing. Confirm current semantics + enforcement live (governance actively changing).
  • Starting budget + bid strategy progression (manual/maximize → tCPA when data allows) + kill threshold.

Read the full file on GitHub · 56 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. 8d ago First seen · 56 lines · 0 tokens per session scan A aef46e24de24

Subscribe to this mod's changes

ads-review is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,194 tokens. 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.