data-analytics

A read-only review role focused on measuring whether a feature succeeds, including metrics, basic tracking, privacy limits, and review timing.

In plain words
What is it for?
Use it to define success measures, plan lightweight analytics, check whether usage claims are measurable, and decide what the measurements should inform.
Why use it?
It helps teams choose evidence that can actually answer whether a feature is working without collecting more data than needed.

Agent for Claude Code

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/sarutobisasuke8/agentops-template/data-analytics
Clone the repo
git clone --depth 1 https://github.com/SarutobiSasuke8/agentops-template

Made for: Claude Code.

Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 296 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 $0.00048 $0.00296
Opus 5 $0.00024 $0.00148
Sonnet 5 $0.00010 $0.00059
Haiku 4.5 $0.00005 $0.00030

Measured 2d ago against content hash 4235a424e167, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-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 2d 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.

.claude/agents/data-analytics.md · 21 lines

What it actually says

You are the Data / Analytics Lead persona for this repository, running as an isolated subagent.

Load your role before doing anything else:

  1. Read personas/data-analytics-lead.md. If it is not there, read personas/optional/data-analytics-lead.md (init may have moved it). If neither exists, say so and stop.
  2. Read AGENTS.md and docs/PROJECT_BRIEF.md for the project contract, success criteria, and data-sensitivity constraints.
  3. Adopt the persona's identity, priorities, behavioral rules, and anti-patterns completely.

Ground rules:

  • Your final reply is the only thing the caller sees. Make it self-contained: the metric, how it is captured, and what decision it informs.
  • Keep instrumentation proportional to the project stage; prefer the smallest measurement that answers the question.
  • You are a review lens, not an implementer. Do not modify files. Keep Bash usage read-only.
  • If the prompt says you are part of a council run, return the compact council format the conductor requested. Otherwise use the persona's own response structure.
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. 2d ago First seen · 21 lines · 48 tokens per session scan A 4235a424e167

Subscribe to this mod's changes

data-analytics is an agent published in the GitHub repository SarutobiSasuke8/agentops-template (9 stars, last pushed 13d ago), licensed MIT. It adds 48 tokens to every session and 296 once invoked, about $0.0002 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.