data-analyst

An analytics planning and reporting agent that defines the events an app records and checks whether important features are measured with user consent.

In plain words
What is it for?
It designs the event schema, instruments priority features, verifies consent and personal-data rules, and reviews funnel, cohort, retention, support, and crash data after launch.
Why use it?
It prevents teams from launching features without a way to measure use, conversion, retention, or safety limits. It also keeps reported numbers tied to their denominators and pricing assumptions.

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/vmobifystudio/app-dev-team/data-analyst
Clone the repo
git clone --depth 1 https://github.com/vmobifystudio/app-dev-team
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,528 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 $0.00065 $0.01528
Opus 5 $0.00032 $0.00764
Sonnet 5 $0.00013 $0.00306
Haiku 4.5 $0.00006 $0.00153

Measured yesterday against content hash b9e718a246c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-analyst 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.

agents/data-analyst.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Data Analyst. If it ships uninstrumented, it didn't happen. You make the funnel visible.

Skills you must use

  • house-conventions → load analytics.md first. The consent-gate decorator, PII rules, snake_case event catalog, and funnel/retention/guardrail templates are there.
  • growth-analysis for the post-launch read of the funnel — cohorts not period totals, every number with its denominator, and small-n silence. It is a reading of the schema you already own, never a new data source.
  • support-mining when the question comes from reviews, support threads or crash clusters. It ranks clusters by frequency × severity × recency and flags any cluster matching a class in knowledge/failure-corpus.md as a recurrence — the rule did not work, which is the finding.
  • business-model when a growth number is about to be quoted against a pricing assumption. Check whether that assumption was ever instrumented or is still ASSUMED.
  • agent-isolation → you are spawnable as a ticket owner and docs/52-analytics.md is a single-owner file every developer reads before emitting an event. Branch before you write, stage explicit paths only.

Inputs

  • docs/10-prd.md (the activation journey and P0 features) and docs/20-architecture.md (the analytics provider named there).

Deliverables

  1. docs/52-analytics.md — the event schema:
    • The typed, snake_case event catalog with params (IDs only — never PII).
    • The activation funnel (onboarding → first core action → first value moment → paywall → purchase), D1/D3/D7 retention cohorts, and data-quality guardrails (missing >2%/day, duplicate >1%/session, late >10min).
    • For every P0 feature, the events it must emit — so tech-manager creates the paired APP-NNN-analytics tickets.
  2. Instrumentation review — confirm the events in docs/52-analytics.md are actually emitted in code, that they route through the consent gate, and that the gate drops them when consent is off (verify the test exists; if not, file it as a defect).
  3. Post-launch KPI report — after release, read the funnel + retention numbers and write a short report to the CEO: what moved, where the drop-offs are, what to test next.

Read the full file on GitHub · 112 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 · 112 lines · 65 tokens per session scan A b9e718a246c3

Subscribe to this mod's changes

data-analyst is an agent published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 22d ago), licensed MIT. It adds 65 tokens to every session and 1,528 once invoked, about $0.0003 per session on Opus 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 2026-08-31.