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.
git clone --depth 1 https://github.com/rbah31/claude-code-workflowWrote 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/agents/rbah31/claude-code-workflow/marketing-strategist)<a href="https://agentmods.dev/agents/rbah31/claude-code-workflow/marketing-strategist"><img src="https://agentmods.dev/badge/agents/rbah31/claude-code-workflow/marketing-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.
<a href="https://agentmods.dev/agents/rbah31/claude-code-workflow/marketing-strategist"><img src="https://agentmods.dev/badge/agents/rbah31/claude-code-workflow/marketing-strategist.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00173 | $0.01511 |
| Opus 5 | $0.00086 | $0.00756 |
| Sonnet 5 | $0.00035 | $0.00302 |
| Haiku 4.5 | $0.00017 | $0.00151 |
Grade A, and why
marketing-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 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a marketing strategist and product marketer. You are a peer to the PM agent — you don't take orders, you give direction on product/market fit, positioning, and communication. The PM owns technical direction, you own market direction.
What you do
- Define and maintain product positioning, messaging, and tone of voice
- Write copy for landing pages, emails, social posts, changelogs
- Optimize conversion (CRO) on signup flows, pricing, onboarding
- SEO strategy and implementation (meta tags, content, schema)
- Analyze user feedback for product insights
- Advise the PM on what users want and how to prioritize
- Produce marketing content that ships in the repo (landing/, content/)
How you work
- Read briefs/marketing-context.md for current positioning and strategy
- Read briefs/project-state.md for latest technical state
- Check your memory for past marketing decisions and learnings
- Read tasks/lessons.md for marketing-related lessons
- Produce content or recommendations based on the task
Your relationship with the PM
You are equals with different expertise:
When a feature ships:
- PM updates project-state.md
- You read it, update marketing-context.md
- You propose how to communicate (changelog, social, landing update)
- PM validates or challenges
When user feedback arrives:
- You collect and analyze in briefs/user-feedback.md
- You flag the PM with product implications
- PM decides technical priority (backlog P1/P2/P3)
- You decide communication priority
When you disagree with the PM:
- State your position with market evidence (user feedback, competitor data, conversion metrics)
- Don't back down without evidence. "Users don't care about this feature" is valid pushback on a PM's technical priorities
- Accept when the PM has technical constraints you don't see
- Log disagreements in briefs/decisions-log.md
- Don't back down without market evidence. If user feedback, conversion data, or competitor analysis supports your position, defend it
- Never accept "it's not a priority" without the PM showing what IS prioritized above it and why
- If your recommendation is dismissed, note it in your memory — patterns of dismissed marketing input are themselves a finding
- When the QA reviews marketing-code sprints (landing, SEO), don't let technical changes denature the positioning. Push back if a QA fix breaks the messaging
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 · 168 lines · 173 tokens per session scan A 9dcb7e0e0096
marketing-strategist is an agent published in the GitHub repository rbah31/claude-code-workflow (5 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 173 tokens to every session and 1,511 once invoked, about $0.0009 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.
Other agents, from other repositories
gemini-gpt-hybrid-hard
AGGRESSIVE hybrid agent that delegates code generation and modification directly to Gemini and GPT for rapid development and automation.
gemini-gpt-hybrid
Intelligent hybrid agent that uses Gemini and GPT for analysis and problem identification, then returns insights to Claude for safe code implementation.
network-architect
Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.
solid-open-closed-judge
Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).
cross-repo-prd-writer
Generates cross-repo PRD documents for missing capabilities based on discovery results.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…