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.
npx skills add brainbytes-dev/everything-claude-marketing --skill martech-stackgit clone --depth 1 https://github.com/brainbytes-dev/everything-claude-marketingWrote 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/skills/brainbytes-dev/everything-claude-marketing/martech-stack)<a href="https://agentmods.dev/skills/brainbytes-dev/everything-claude-marketing/martech-stack"><img src="https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/martech-stack/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/skills/brainbytes-dev/everything-claude-marketing/martech-stack"><img src="https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/martech-stack.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 | $0.00028 | $0.03428 |
| Opus 5.5 | $0.00011 | $0.01371 |
| Sonnet 5.5 | $0.00006 | $0.00686 |
| Haiku 4.5 | $0.00003 | $0.00343 |
Grade A, and why
martech-stack 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.
How it starts
The opening of the file, as written. The whole thing — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Martech Stack
When to Activate
Use this skill when evaluating or selecting marketing technology tools, auditing an existing martech stack for redundancy or gaps, planning a martech migration, building a marketing ops infrastructure from scratch, deciding between building custom solutions or buying off-the-shelf, budgeting for marketing technology, or when someone asks to "recommend tools," "audit our stack," or "evaluate marketing platforms." Also activate when data is siloed across tools or when the team is frustrated by tool complexity.
First Questions
Before evaluating or recommending martech, clarify:
- What is the current stack? (list every tool the marketing team uses, including free and unofficial ones)
- What is the company stage and size? (startup, scaleup, enterprise — determines complexity tolerance)
- What is the marketing ops maturity? (ad hoc, defined processes, optimized, or data-driven)
- What problems are you trying to solve? (don't start with tools — start with pain points)
- What is the budget? (monthly/annual spend on martech — include hidden costs like implementation and training)
- Who will manage these tools? (dedicated ops person, shared responsibility, agency — determines complexity ceiling)
- What does the tech stack outside marketing look like? (CRM owned by sales? Analytics by product? Data warehouse? — integration matters)
Core Rules
- Problems first, tools second. Never recommend a tool without first understanding the workflow it needs to support. A tool without a process is shelfware.
- Integration beats features. A tool that connects to your existing stack is worth more than a best-in-class tool that creates a data silo.
- The best tool is the one that gets used. Adoption matters more than capability. A simple tool used daily beats a powerful tool used quarterly.
- Every tool has a total cost of ownership. License fee is 30-50% of the real cost. Add implementation, training, maintenance, data migration, and opportunity cost of switching.
- Stack complexity should match team maturity. A 3-person marketing team does not need a CDP, ABM platform, and marketing attribution tool. They need a CRM, email tool, and analytics.
- Audit before adding. Before buying a new tool, check if an existing tool can do the job. Most marketing teams use only 30-40% of their tools' capabilities.
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.
- 2mo ago First seen · 295 lines · 28 tokens per session scan A 4195543ac01f
martech-stack is a skill published in the GitHub repository brainbytes-dev/everything-claude-marketing (10 stars, last pushed 7mo ago), licensed MIT. It adds 28 tokens to every session and 3,428 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.
martech-stack compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| martech-stackbrainbytes-dev/everything-claude-marketing | Skill | 10 | 7mo ago | MIT | A | 28 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |