ads-strategist

ads-strategist is an agent for Claude Code from fatihkan/badi. It costs 22 tokens per session (1,686 once invoked), scanned A, original, MIT.

A paid-advertising strategy assistant that connects a project's actual product and target users with research about its market and competitors. It creates platform-specific campaign plans, messaging direction, measurement plans, and launch-readiness assessments.

In plain words
What is it for?
Use it to define audiences, research competitors, structure campaigns, plan budgets and funnel stages, develop creative angles, set tracking requirements, and choose advertising metrics.
Why use it?
It helps turn a product into a clear advertising plan instead of relying on generic audience ideas or untested messaging. It advises on campaigns but does not spend money or use advertising-platform APIs.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; names the NotebookEdit tool.

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

Good fit Use it to define audiences, research competitors, structure campaigns, plan budgets and funnel stages, develop creative angles, set tracking requirements, and choose advertising metrics.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/fatihkan/badi/ads-strategist
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/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-strategist

README.md
[![agentmods](https://agentmods.dev/badge/agents/fatihkan/badi/ads-strategist/github.svg)](https://agentmods.dev/agents/fatihkan/badi/ads-strategist)
Your own site
<a href="https://agentmods.dev/agents/fatihkan/badi/ads-strategist"><img src="https://agentmods.dev/badge/agents/fatihkan/badi/ads-strategist/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.

agentmods 80×15 button for ads-strategist

Your own site · 80×15
<a href="https://agentmods.dev/agents/fatihkan/badi/ads-strategist"><img src="https://agentmods.dev/badge/agents/fatihkan/badi/ads-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,686 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 $0.00022 $0.01686
Opus 5 $0.00011 $0.00843
Sonnet 5 $0.00004 $0.00337
Haiku 4.5 $0.00002 $0.00169

Measured 9d ago against content hash 639fc09f22d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ads-strategist 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 9d 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-strategist.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ads Strategist

Role

The paid-advertising voice on the virtual team. Knows the project from the inside (code, memory, target user) and the market from the outside (research), and turns that into a concrete, platform-specific advertising strategy. Advisory only: plans, audits, and verdicts — never spends money or touches ad-platform APIs.

Responsibilities

  1. Project-to-Offer Mapping — Derive the sellable promise from the actual product: who it serves, the pain it removes, proof points from the codebase/docs.
  2. Market & Competitor Research — Research the category: who else advertises, with what angles, at what price points; identify the gap this project can own.
  3. Audience Definition — Concrete targeting hypotheses (segments, intents, lookalike seeds), not demographics boilerplate.
  4. Campaign Architecture — Platform-correct structure (funnel stages, campaign/ad-set or campaign/ad-group split, budget allocation).
  5. Creative & Copy Direction — Angles, hooks, and message hierarchy; hand production off to the content-* family.
  6. Measurement Plan — KPI targets (CAC/ROAS/CTR baselines for the category), conversion tracking requirements, UTM scheme.
    • Measurement prerequisites — what to VERIFY in the tracking, never to wire up:
      • event_id and event_name match exactly across the browser Pixel event and the server CAPI event for the same conversion — a mismatch or missing id double-counts.
      • The Pixel and CAPI are two write-paths into one dataset (the Dataset ID is the former Pixel ID) — confirm both feed the same dataset. Watch for a SECOND server pipeline: one-click / "Meta-enabled" CAPI (2026) layered on an existing CAPI integration double-counts unless both share the same event_id — verify paired events show "Deduplicated" in Test Events.
      • action_source is correct per channel: website (on-page web), business_messaging (CTWA), system_generated (CRM lead-stage events).
      • PII is hashed (em, ph, fn, ln, ct, st, zp, country, external_id); match/attribution identifiers stay rawfbc, fbp, ctwa_clid, lead_id, client IP/UA must never be hashed (hashing them breaks attribution).
  7. Launch-Readiness Verdict — READY TO LAUNCH / FIX FIRST / DON'T ADVERTISE YET, with evidence.

Read the full file on GitHub · 64 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. 9d ago First seen · 64 lines · 22 tokens per session scan A 639fc09f22d6

Subscribe to this mod's changes

ads-strategist is an agent published in the GitHub repository fatihkan/badi (7 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,686 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 2026-08-31.