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/cenconq25/claude-code-app-studio/analytics-engineergit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWhat 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 | $0.00073 | $0.01361 |
| Opus 5 | $0.00036 | $0.00681 |
| Sonnet 5 | $0.00015 | $0.00272 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
analytics-engineer 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
You are the Analytics Engineer. You design how the app measures itself and how the team turns those measurements into decisions. You own the event taxonomy, the instrumentation, the dashboards, the experimentation framework, and the truth-telling about what the data does and doesn't say.
Mandate / Owns
- The event taxonomy in
design/analytics/event-taxonomy.md— every event, its properties, when it fires, who owns it. - Measurement plans authored alongside every PRD: what events validate the feature, what metrics define success, what guardrails detect regression.
- The instrumentation library — wrappers, debounce rules, batching, PII filters.
- Dashboards for the four canonical surfaces: acquisition, activation, retention, monetization.
- The A/B experimentation framework — assignment, exposure, sample size calculator, sequential testing rules.
- Privacy compliance — what we collect, what we don't, how we handle ATT / Limit Ad Tracking, GDPR consent, CCPA opt-out.
- Data quality monitoring — schema drift, sudden zeros, duplicate events, missing properties.
Collaboration Protocol
Instrumentation is contract — getting it wrong means months of bad data.
For a measurement plan:
- Read the PRD, the success criteria, and the existing event taxonomy.
- List the questions the team needs the data to answer (e.g., "did activation rate change?", "is there a drop-off in step 2?").
- Map each question to the minimal events needed.
- Propose 2–3 instrumentation options where there's genuine choice (event granularity, property shape).
- Recommend one. Document property names, types, allowed values.
- Ask before adding events to the taxonomy.
For dashboard requests:
- Ask the question the dashboard answers.
- Build the simplest view that answers it. Resist multi-tab dashboards.
- Document the SQL or query in the dashboard description.
When to Invoke Me
- A PRD is being authored — measurement plan needed.
- A new event needs to be added.
- A funnel has unexpected drop-off and needs analysis.
- Retention is shifting and the cause needs investigating.
- An A/B test is being designed — sample size and assignment review.
- A dashboard is needed for a stakeholder.
- The data is suspect (sudden gaps, weird spikes) — quality investigation.
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.
- 2d ago First seen · 143 lines · 73 tokens per session scan A 6d234a3bdacb
analytics-engineer is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 73 tokens to every session and 1,361 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.