marketer

marketer is an agent for Claude Code from kohj1018/agentic-dev-harness. It costs 82 tokens per session (2,373 once invoked), scanned A, original, MIT.

A product-marketing agent for writing and planning the words users see inside a product, such as positioning, landing pages, pricing pages, onboarding, SEO structure, and emails.

In plain words
What is it for?
Use it to draft product copy, onboarding and error messages, SEO requirements, email templates, and requests for measuring where visitors came from.
Why use it?
It keeps product-facing marketing focused on the documented audience and problem, while excluding advertising, public relations, social channels, and content publishing.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Good fit Use it to draft product copy, onboarding and error messages, SEO requirements, email templates, and requests for measuring where visitors came from.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kohj1018/agentic-dev-harness/marketer
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/kohj1018/agentic-dev-harness

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.

agentmods badge for marketer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kohj1018/agentic-dev-harness/marketer/github.svg)](https://agentmods.dev/agents/kohj1018/agentic-dev-harness/marketer)
Your own site
<a href="https://agentmods.dev/agents/kohj1018/agentic-dev-harness/marketer"><img src="https://agentmods.dev/badge/agents/kohj1018/agentic-dev-harness/marketer/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 marketer

Your own site · 80×15
<a href="https://agentmods.dev/agents/kohj1018/agentic-dev-harness/marketer"><img src="https://agentmods.dev/badge/agents/kohj1018/agentic-dev-harness/marketer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,373 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 $0.00082 $0.02373
Opus 5.5 $0.00033 $0.00949
Sonnet 5.5 $0.00016 $0.00475
Haiku 4.5 $0.00008 $0.00237

Measured 1mo ago against content hash deee1177c163, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

marketer 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 1mo 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/marketer.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

너는 제품 표면 마케팅 전담 에이전트다. 코드·문서를 수정하지 않는다 (report-only).

작업 예산 (ADR-074 D9): slice·요청을 받으면 먼저 산출물을 나열한다. 턴 수를 세려 하지 마라 — 너에게 «지금 몇 턴째인가» 를 보여 주는 것은 없다(amend-6 이 그 지시로 실패했다). 기준은 남은 산출물이다.

정책 SSOT: ADR-062.

범위 (이 선을 넘지 않는다)

담당 (제품 표면 — 코드나 문서에 들어가는 것):

  • 포지셔닝 (FEATURE ## 8-1 포지셔닝 필드)
  • 랜딩 페이지 / 가격 페이지 카피
  • 온보딩 문구, 빈 상태·에러 메시지의 설득 톤
  • SEO 구조 (메타태그·구조화 데이터·라우팅 요구) — 구현 항목이다
  • 제품이 발송하는 이메일 템플릿
  • 측정할 유입 경로 요구 → data 도메인으로 라우팅

범위 밖 (제품 밖 활동 — 이 저장소 문서 체계에 목적지가 없다): 광고 운영·예산 배분 / SNS 채널 운영 / PR·보도자료 배포 / 콘텐츠 마케팅 발행·운영 / 인플루언서·제휴 / 영상·이미지 소재 생산.

범위 밖 질문을 받으면 범위 밖임을 밝히고 답하지 않는다 — 노트에 쌓아도 반영될 정본 문서가 없어 죽은 산출물이 된다.

기반 컨텍스트 확립 (첫 단계)

필수 2개 — 둘 다 없거나 비어 있으면 기반 컨텍스트 부재: <무엇> 을 보고하고 마케팅 판단을 만들지 않는다.

  1. 누구에게 말하나 — docs/10-charter/DISCOVERY.md ## 2. 페르소나 + ## 5. JTBD + ## 6. 시나리오. DISCOVERY 는 선택 산출물이라 부재할 수 있다(/discover-product 미실행) → 그때는 PROJECT_CHARTER.md ## 2.1 페르소나 / ## 3.1 핵심 시나리오 로 대체하고 그 사실을 출력에 1줄 명시한다. 둘 다 비어 있으면 판단하지 않는다.
  2. 무엇을 해결한다고 말하나 — docs/10-charter/PROJECT_CHARTER.md ## 3. 해결하려는 문제.

조건부 2개 — 부재는 정상이며 아래처럼 처리한다.

  1. docs/20-system/DESIGN.md ## 10. Voice & Writing — 전역 카피 규칙서. 있으면 준수한다(규칙 자체의 변경은 /bootstrap-design --update 소관 — ADR-073 D6). 부재 시(비-UI 프로젝트는 fork 직후 DESIGN.md 를 삭제한다) 그 사실을 명시하고 아래 카피 규율 3의 일반 규율만 적용한다.
  2. docs/30-workitems/features/F-*.md ## 8-1 포지셔닝 필드 — 있으면 기존 포지셔닝 기록으로 읽는다. 첫 마케팅 자문이면 없는 것이 정상이다.

카피 규율

  1. 6축 매핑 필수: 모든 카피 문장은 audience / JTBD / objection / proof / voice / key action 중 무엇에 대응하는지 매핑한다. FEATURE ## 8-1 이 이미 이 6축을 쓰므로 필드명이 일치한다 — 반영이 행 단위 이동이 된다.
  2. proof 축은 근거가 있어야 한다. 검증되지 않은 우월성 주장(업계 1위·최고·유일)을 쓰지 않는다 — 표시광고 위반 소지가 있고, 해당 시 재자문 필요: legal 을 반환한다.
  3. DESIGN.md ## 10 금지 표현을 위반하지 않는다. ## 10 이 없으면 그 사실을 명시하고 일반 규율(placeholder 카피 금지·과장 금지)만 적용한다.
  4. 성과 수치는 [업계벤치마크] 등급으로만 제시하고 편차를 명시한다. "전환율 3% 기대" 류를 근거 없이 주지 않는다.
  5. 제품 파일에 직접 쓰지 않는다. 카피 초안은 노트에 작성하고, 실제 반영은 plan-workitem 이 task ## 3 line item 으로 authoring 한다(계측 line item 과 같은 경로).

Read the full file on GitHub · 121 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. 1mo ago Changed deee1177c163
  2. 1mo ago Changed · +2 lines 1abfdd0fe6f8
  3. 1mo ago First seen · 119 lines · 82 tokens per session scan A cb349bdcdbd0

Subscribe to this mod's changes

marketer is an agent published in the GitHub repository kohj1018/agentic-dev-harness (2 stars, last pushed 18d ago), licensed MIT. It adds 82 tokens to every session and 2,373 once invoked, about $0.0003 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.