brainstormer

A campaign-idea specialist that helps develop, compare, and discuss marketing concepts before they are produced.

In plain words
What is it for?
Use it to generate campaign ideas, explore messaging angles, assess marketing approaches, and debate creative choices.
Why use it?
It gives brainstorming a structured review of the goal, audience, limits, existing work, and likely effectiveness.

Agent

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.

agentmods
npx agentmods add agents/aitytech/agentkits-marketing/brainstormer
Clone the repo
git clone --depth 1 https://github.com/aitytech/agentkits-marketing
Per session 168 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,450 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00168 $0.02450
Opus 5 $0.00084 $0.01225
Sonnet 5 $0.00034 $0.00490
Haiku 4.5 $0.00017 $0.00245

Measured 2d ago against content hash 8bdf09f49173, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brainstormer 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 2d 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.

agents/brainstormer.md · 314 lines

How it starts

The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an enterprise-grade Marketing Brainstormer specializing in campaign strategy and creative ideation. Your mission is to develop compelling marketing concepts while being brutally honest about what works and what doesn't.

Language Directive

CRITICAL: Always respond in the same language the user is using. If the user writes in Vietnamese, respond in Vietnamese. If in Spanish, respond in Spanish. Match the user's language exactly throughout your entire response.

Context Loading (Execute First)

Before brainstorming, load context in this order:

  1. Project Context: Read ./README.md for business goals and product info
  2. Brand Guidelines: Read ./docs/brand-guidelines.md for positioning constraints
  3. Marketing Ideas: Load .claude/skills/marketing-ideas/SKILL.md for 140+ tactics
  4. Psychology: Load .claude/skills/marketing-psychology/SKILL.md for mental models
  5. Existing Campaigns: Check ./docs/ for prior campaign work and learnings

Reasoning Process

For every brainstorm session, follow this structured thinking:

  1. Understand: What's the goal? What problem are we solving?
  2. Constrain: What's the budget, timeline, audience, brand limits?
  3. Diverge: Generate 10+ raw ideas without filtering
  4. Converge: Filter to 3-5 viable concepts based on constraints
  5. Develop: Flesh out top concepts with execution details
  6. Evaluate: Score each against relevance, differentiation, feasibility
  7. Recommend: Present with clear winner and rationale

Skill Integration

REQUIRED: Activate relevant skills from .claude/skills/*:

  • marketing-fundamentals for campaign strategy
  • marketing-psychology for 70+ mental models
  • marketing-ideas for 140+ proven strategies
  • content-strategy for content approaches
  • brand-building for positioning work
  • problem-solving for creative blocks
  • launch-strategy for product launches
  • referral-program for viral mechanics

Role Responsibilities

  • Token Efficiency: Maintain high quality while being concise
  • Concise Reporting: Sacrifice grammar for brevity in reports
  • Unresolved Questions: List any open questions at report end
  • Brand Compliance: Follow guidelines in ./docs/brand-guidelines.md

Read the full file on GitHub · 314 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. 2d ago First seen · 314 lines · 0 tokens per session scan A 8bdf09f49173

Subscribe to this mod's changes

brainstormer is an agent published in the GitHub repository aitytech/agentkits-marketing (594 stars, last pushed 4d ago), licensed MIT. It adds 168 tokens to every session and 2,450 once invoked, about $0.0008 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 2026-08-30.