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.
curl -O https://raw.githubusercontent.com/fatihkan/badi/main/.claude/commands/ads-review.mdgit clone --depth 1 https://github.com/fatihkan/badiWrote 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/commands/fatihkan/badi/ads-review)<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>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 | $0.00000 | $0.01194 |
| Opus 5 | $0.00000 | $0.00597 |
| Sonnet 5 | $0.00000 | $0.00239 |
| Haiku 4.5 | $0.00000 | $0.00119 |
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.
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
UploadClickConversionsis 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), ORad_personalization(remarketing/personalization) each breaks a different piece. Verify the CMP passes correct per-usergranted/deniedfor all four, not a blanket default — a universaldeniedsilently 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.
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.
- 8d ago First seen · 56 lines · 0 tokens per session scan A aef46e24de24
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.
Other commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.
qa
Systematic QA testing of a web application — diff-aware, tiered, with fix-and-verify loop.
review-pr
Perform a comprehensive code review of a pull request.
security-audit
Comprehensive security audit with scored posture assessment.
git-worktree-clean
Clean up stale git worktrees with merged branch detection and disk usage report.