campaign-concepts

campaign-concepts is a skill for Claude Code from brainbytes-dev/everything-claude-marketing. It costs 26 tokens per session (3,981 once invoked), scanned A, original, MIT.

A guide to creating a central idea for a marketing campaign and carrying it consistently across channels.

In plain words
What is it for?
Use it to brainstorm campaign ideas, write creative briefs, name campaigns, plan launches, and build brand or seasonal campaigns.
Why use it?
It helps campaigns feel connected instead of becoming a collection of unrelated posts, ads, and activities.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the everything-claude-marketing plugin — 72 skills, 22 commands, 18 agents, 2 hooks shipped together

Good fit Use it to brainstorm campaign ideas, write creative briefs, name campaigns, plan launches, and build brand or seasonal campaigns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brainbytes-dev/everything-claude-marketing/campaign-concepts
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.

Any agent
npx skills add brainbytes-dev/everything-claude-marketing --skill campaign-concepts
Clone the repo
git clone --depth 1 https://github.com/brainbytes-dev/everything-claude-marketing

Made for: Claude Code.

Or install everything-claude-marketing, the plugin that ships this one along with the rest of its 72 skills, 22 commands, 18 agents, 2 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 campaign-concepts

README.md
[![agentmods](https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/campaign-concepts/github.svg)](https://agentmods.dev/skills/brainbytes-dev/everything-claude-marketing/campaign-concepts)
Your own site
<a href="https://agentmods.dev/skills/brainbytes-dev/everything-claude-marketing/campaign-concepts"><img src="https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/campaign-concepts/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 campaign-concepts

Your own site · 80×15
<a href="https://agentmods.dev/skills/brainbytes-dev/everything-claude-marketing/campaign-concepts"><img src="https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/campaign-concepts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,981 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 $0.00026 $0.03981
Opus 5.5 $0.00010 $0.01592
Sonnet 5.5 $0.00005 $0.00796
Haiku 4.5 $0.00003 $0.00398

Measured 2mo ago against content hash 8b6f085d02f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

campaign-concepts 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 2mo 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.

skills/creative/campaign-concepts/SKILL.md · 350 lines

How it starts

The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Campaign Concepts

When to Activate

Use this skill when brainstorming a new marketing campaign, developing a "big idea" that unifies messaging across channels, writing a creative brief, naming a campaign, planning a seasonal or cultural moment campaign, developing a product launch campaign, creating a brand campaign, or when someone asks to "come up with a campaign idea" or "create a campaign concept." Also activate when existing campaigns feel tactical and disconnected — lacking a unifying creative thread.

First Questions

Before developing a campaign concept, clarify:

  1. What is the business objective? (launch, awareness, lead gen, sales, repositioning, recruitment)
  2. Who is the target audience? (persona, awareness level, relationship to brand)
  3. What is the single most important message? (the one thing the audience should think, feel, or do)
  4. What channels will this campaign run on? (determines creative format constraints)
  5. What is the budget? (dictates production ambition)
  6. What is the timeline? (concept to launch window)
  7. Are there brand guidelines or mandatories? (tone, visual identity, legal requirements, compliance)

Core Rules

  1. A campaign is not a collection of tactics. A campaign is a unified creative idea expressed across multiple touchpoints. If you can't describe the concept in one sentence, it's not a concept — it's a task list.
  2. Start with the insight, not the execution. The best campaigns are built on a human truth — something the audience feels deeply but hasn't articulated. Find the insight first, then build the creative around it.
  3. One campaign, one message. Trying to communicate three things means communicating nothing. Pick the single most important message and make everything serve it.
  4. The audience is the hero. The campaign should be about the audience's world, not the brand's achievements. The brand is the enabler, not the protagonist.
  5. Good concepts are channel-agnostic. A great idea works as a billboard, a social post, an email, and a conversation. If it only works in one format, it's an execution, not a concept.
  6. Simple ideas win. If you need a paragraph to explain the concept, it's too complex. The best campaign ideas can be understood in 5 seconds.

Read the full file on GitHub · 350 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. 2mo ago First seen · 350 lines · 26 tokens per session scan A 8b6f085d02f1

Subscribe to this mod's changes

campaign-concepts is a skill published in the GitHub repository brainbytes-dev/everything-claude-marketing (10 stars, last pushed 7mo ago), licensed MIT. It adds 26 tokens to every session and 3,981 once invoked, about $0.0001 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 2026-09-03.

Related

campaign-concepts compared with skills from other repositories

campaign-concepts next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
campaign-conceptsbrainbytes-dev/everything-claude-marketingSkill107mo agoMITA26Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code