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 agentmods add agents/nxtg-ai/forge-plugin/analyticsgit clone --depth 1 https://github.com/nxtg-ai/forge-pluginWhat 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 | $0.00000 | $0.01924 |
| Opus 5 | $0.00000 | $0.00962 |
| Sonnet 5 | $0.00000 | $0.00385 |
| Haiku 4.5 | $0.00000 | $0.00192 |
Grade A, and why
analytics 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 yesterday.
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analytics
Instruments your application with meaningful metrics -- performance timing, usage tracking, quality KPIs, and developer experience measurements that drive decisions with data, not guesses.
| Level | L1 Vibe Coder |
| Category | Domain Specialist |
| Model | Haiku |
What It Does
The Analytics agent turns "I think the app is slow" into "agent.execution p95 is 340ms, up 45% from last week." It instruments code with metrics that matter: performance timing (bootstrap, API latency, build duration), quality indicators (test pass rate, type violations, security issues), usage patterns (feature adoption, command frequency, session duration), and developer experience measurements (time to first interaction, task completion rate, context restoration success).
What separates this agent from "add console.time everywhere" is its focus on actionable insights. Every metric it tracks is tied to a decision. Bootstrap time under 30 seconds? Good, no action needed. Over 30 seconds? Investigate which initialization step is the bottleneck. Test pass rate at 100%? Good. Dropped to 95%? Identify and fix the failing tests. The Analytics agent does not collect data for its own sake -- it collects data that tells you when something needs attention and where to look.
The agent also understands the difference between snapshots and trends. A single measurement of 28-second bootstrap time means little. Bootstrap time trending upward over three weeks means something is getting heavier and needs investigation. The Analytics agent structures its reports around trends and direction, not just current values, because trends are what drive smart engineering decisions.
When to Use It
- When you need to understand usage patterns: When you want data on which features are used most, how long sessions last, or which agents get invoked the most frequently.
- When you need to track a new metric: When a performance budget, quality target, or business KPI needs to be instrumented and monitored over time.
- When preparing a report: When you need a structured snapshot of performance, quality, and usage metrics for a release review, sprint retrospective, or stakeholder update.
- When investigating a trend: When you suspect performance is degrading, adoption is stalling, or error rates are climbing, and need data to confirm or refute.
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.
- yesterday First seen · 153 lines · 0 tokens per session scan A 65b63b14f7b4
analytics is an agent published in the GitHub repository nxtg-ai/forge-plugin (5 stars, last pushed 12d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,924 tokens. 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 2026-08-31.
Other agents, from other repositories
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
data-pipeline-engineer
Data pipeline specialist: embeddings, chunking strategies, vector indexes, data transformation for AI consumption.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
emulate-engineer
Stateful API emulation via Vercel emulate. Seeds GitHub/Vercel/Google/Slack/Apple/Entra/AWS/MongoDB/Okta/Resend/Stripe/Clerk/Linear, webhooks, port isolation, Next.js adapter. Use to replace flaky API mocks.
TESTING
This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.