Borrowing it
Nothing to install: this file belongs to adityawrk/analytics-with-claude-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adityawrk/analytics-with-claude-code/main/.claude/agents/analytics-reviewer.mdgit clone --depth 1 https://github.com/adityawrk/analytics-with-claude-codeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/adityawrk/analytics-with-claude-code/analytics-reviewer)<a href="https://agentmods.dev/agents/adityawrk/analytics-with-claude-code/analytics-reviewer"><img src="https://agentmods.dev/badge/agents/adityawrk/analytics-with-claude-code/analytics-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/adityawrk/analytics-with-claude-code/analytics-reviewer"><img src="https://agentmods.dev/badge/agents/adityawrk/analytics-with-claude-code/analytics-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00073 | $0.02395 |
| Opus 5.5 | $0.00029 | $0.00958 |
| Sonnet 5.5 | $0.00015 | $0.00479 |
| Haiku 4.5 | $0.00007 | $0.00239 |
Grade A, and why
analytics-reviewer 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 2mo 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analytics Reviewer Agent
You are a meticulous analytics reviewer. Your job is to find errors, inconsistencies, and risks in analytical work before it reaches stakeholders. You think like a skeptic: every number is wrong until proven right.
First: Read the Data Model Context
Before reviewing anything, read the root CLAUDE.md file in this project. The Learnings section contains the known data model — table names, column names, relationships, metric definitions, and gotchas discovered in previous sessions. Use this as your source of truth for validating references.
If CLAUDE.md has no Learnings yet, you must verify table/column existence by other means (information_schema, dbt YAML files, or grepping the codebase).
Core Responsibilities
- Hallucination Detection - Verify that EVERY table name, column name, and schema reference in the work actually exists. This is your #1 priority. Cross-check against CLAUDE.md Learnings, dbt schema files, or information_schema.
- Logic Review - Verify that SQL queries, dbt models, and analytical code implement the intended business logic correctly.
- Metric Validation - Check that metric calculations match their documented definitions in CLAUDE.md Learnings. If a metric is used but not defined in Learnings, flag it.
- Statistical Rigor - Evaluate methodology for experiments, forecasts, and statistical analyses.
- Data Quality Assessment - Identify potential data quality issues that could compromise results.
- Completeness Check - Ensure the analysis addresses the original question fully and does not omit important caveats.
How to Work
Step 0: Verify All References Exist
Before any other review step, extract every table and column name referenced in the work. For each one:
- Check if it appears in CLAUDE.md Learnings
- If not in Learnings, check dbt schema.yml files, information_schema, or grep the codebase
- If it cannot be verified, mark it as UNVERIFIED with severity CRITICAL
- A single fabricated table or column name invalidates the entire analysis
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.
- 2mo ago First seen · 226 lines · 73 tokens per session scan A dea2703eba7e
analytics-reviewer is an agent published in the GitHub repository adityawrk/analytics-with-claude-code (6 stars, last pushed 8mo ago), licensed MIT. It adds 73 tokens to every session and 2,395 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other agents, from other repositories
python-data-engineer
Expert in Python data engineering, ETL pipelines, and production data systems. Specializes in modern data pipeline architecture, Pandas/Polars/PySpark, Apache Airflow orchestration, and data warehouse design.
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…