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 0xranx/agentbrief --skill analytics-setupgit clone --depth 1 https://github.com/0xranx/agentbriefWrote 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/0xranx/agentbrief/analytics-setup)<a href="https://agentmods.dev/skills/0xranx/agentbrief/analytics-setup"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/analytics-setup/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/0xranx/agentbrief/analytics-setup"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/analytics-setup.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 | $0.00074 | $0.00888 |
| Opus 5.5 | $0.00030 | $0.00355 |
| Sonnet 5.5 | $0.00015 | $0.00178 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
analytics-setup 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 1mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analytics Setup
You are setting up product analytics that answer real business questions. Your goal is to create a tracking plan that captures meaningful user behavior without drowning in noise.
Process
1. Define Key Questions
Before adding any tracking code, list the top 5 questions you need to answer:
- Are users activating? (Reaching the "aha moment")
- Are users coming back? (Retention)
- Where do users drop off? (Funnel leaks)
- Which features drive engagement? (Feature adoption)
- What brings users to the product? (Attribution)
2. Design the Event Taxonomy
Use a consistent naming convention:
[object]_[action]
Examples:
- page_viewed
- signup_started
- signup_completed
- feature_used
- subscription_started
- subscription_cancelled
- error_occurred
Rules:
- Past tense for completed actions (
signup_completednotsignup) - Snake_case, lowercase
- Object first, then action
- Include properties for context, not in the event name
3. Core Events (Every Product Needs These)
// Identification
analytics.identify(userId, {
email: user.email,
created_at: user.createdAt,
plan: user.plan,
});
// Page / Screen Views
analytics.page('Dashboard');
// Activation Funnel
analytics.track('signup_started', { source: 'landing_page' });
analytics.track('signup_completed', { method: 'google_oauth' });
analytics.track('onboarding_step_completed', { step: 1, step_name: 'create_workspace' });
analytics.track('activation_completed'); // User hit the "aha moment"
// Feature Usage
analytics.track('feature_used', {
feature_name: 'export_csv',
context: 'dashboard',
});
// Revenue
analytics.track('subscription_started', {
plan: 'pro',
billing_cycle: 'annual',
mrr: 29,
});
4. Platform Selection Guide
| Tool | Best For | Price |
|---|---|---|
| PostHog | Self-hosted, open source, full suite | Free (self-hosted) |
| Mixpanel | Event analytics, funnels, retention | Free up to 20M events |
| Amplitude | Product analytics at scale | Free up to 10M events |
| GA4 | Marketing analytics, attribution | Free |
| Plausible | Privacy-friendly, simple web analytics | $9/mo |
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.
- 1mo ago First seen · 110 lines · 74 tokens per session scan A 4cb20c677628
analytics-setup is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 6mo ago), licensed MIT. It adds 74 tokens to every session and 888 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
multi-agent-design
A guide to deciding when several AI agents should work together and how they should share tasks, context, and files. It compares peer, manager-led, and decentralised arrangements and explains common coordination failures.
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
context-engineering
A guide to organizing the instructions and information an AI agent receives at each step. It covers system prompts, tool descriptions, conversation history, on-demand skills, and protections against unsafe outside content.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
loop-engineering
A guide to building reliable loops for AI agents that plan, act, check their work, and continue until a task is truly complete. It includes independent verification and a proposer-reviewer pattern in which one agent's work is checked using outside evidence.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.