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 utm-trackinggit 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/utm-tracking)<a href="https://agentmods.dev/skills/brainbytes-dev/everything-claude-marketing/utm-tracking"><img src="https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/utm-tracking/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/utm-tracking"><img src="https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/utm-tracking.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 | $0.00033 | $0.03523 |
| Opus 5.5 | $0.00013 | $0.01409 |
| Sonnet 5.5 | $0.00007 | $0.00705 |
| Haiku 4.5 | $0.00003 | $0.00352 |
Grade A, and why
utm-tracking 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UTM Tracking
When to Activate
Use this skill when setting up UTM tracking for a new marketing program, designing or standardizing naming conventions, building campaign tracking systems, auditing existing UTM data for inconsistencies, troubleshooting attribution issues in analytics, creating UTM governance documentation for a team, or when someone asks about "campaign tracking," "UTM parameters," or "attribution setup." Also activate when analytics data is unreliable due to inconsistent or missing tracking.
First Questions
Before designing a UTM system, clarify:
- What analytics platform is in use? (GA4, Mixpanel, HubSpot, etc. — UTM behavior varies by platform)
- What channels are active? (paid search, paid social, email, organic social, referral, display, affiliate)
- How many people create tracking URLs? (1 person = light governance needed. 10+ people = strict governance essential)
- Is there an existing naming convention? (audit before replacing — migration requires careful planning)
- What decisions will be made from this data? (channel allocation, campaign ROI, content optimization)
- Is there a CRM or MAP that captures UTMs? (UTMs flowing into HubSpot or Salesforce enable closed-loop attribution)
Core Rules
- Consistency is everything. A UTM system is only as good as its most inconsistent user. One person writing "facebook" while another writes "Facebook" and a third writes "fb" creates three separate channels in analytics.
- Lowercase always. UTMs are case-sensitive. "Email" and "email" are different values in GA4. Enforce lowercase in every parameter, always.
- Use separators consistently. Pick one separator (hyphens or underscores) and never deviate. Hyphens are the most common convention.
- Less is more. Don't over-parameterize. If you can't act on the data a parameter provides, don't track it. Too many granular UTMs fragment your data.
- UTMs are for external traffic only. Never use UTMs on internal links (site navigation, in-app links). They restart the session in GA4, destroying your attribution data.
- Document and share. A naming convention that lives in one person's head is worthless. It must be documented, shared, and enforced.
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 · 298 lines · 33 tokens per session scan A 1a86bbd9d929
utm-tracking is a skill published in the GitHub repository brainbytes-dev/everything-claude-marketing (10 stars, last pushed 7mo ago), licensed MIT. It adds 33 tokens to every session and 3,523 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.
utm-tracking compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| utm-trackingbrainbytes-dev/everything-claude-marketing | Skill | 10 | 7mo ago | MIT | A | 33 | 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 |