analytics

An analytics agent that adds measurements for application performance, quality, usage, and the developer experience.

In plain words
What is it for?
Use it to track API and startup timing, build duration, test pass rates, type and security issues, feature usage, command frequency, and task completion.
Why use it?
It turns vague reports such as “the app is slow” into measurable results that can point to a specific problem. The metrics are chosen to support decisions rather than simply adding timers everywhere.

Agent

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.

agentmods
npx agentmods add agents/nxtg-ai/forge-plugin/analytics
Clone the repo
git clone --depth 1 https://github.com/nxtg-ai/forge-plugin
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,924 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01924
Opus 5 $0.00000 $0.00962
Sonnet 5 $0.00000 $0.00385
Haiku 4.5 $0.00000 $0.00192

Measured yesterday against content hash 65b63b14f7b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

docs/agents/analytics.md · 153 lines

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.

Read the full file on GitHub · 153 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. yesterday First seen · 153 lines · 0 tokens per session scan A 65b63b14f7b4

Subscribe to this mod's changes

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.