bi-reviewer

bi-reviewer is an agent for Claude Code from revfactory/harness-100. It costs 41 tokens per session (743 once invoked), scanned A, original, Apache-2.0.

A quality reviewer for business intelligence systems, checking whether data models, KPI calculations, dashboards, and reports agree. Business intelligence means using organized data to support decisions.

In plain words
What is it for?
It helps cross-check formulas against database columns, compare dashboards with reports, verify end-to-end data flow, assess usability, and classify issues by severity.
Why use it?
It finds contradictions and broken links between stages that may not be visible when each file or report is checked alone.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

Good fit It helps cross-check formulas against database columns, compare dashboards with reports, verify end-to-end data flow, assess usability, and classify issues by severity.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/revfactory/harness-100/bi-reviewer
About the project

Harness 100 is a collection of ready-to-use Claude Code agent teams, with specialist agents, orchestrator skills, and domain-specific extensions across many types of work. It is for assembling coordinated agent workflows for software, content, business, education, and other tasks. The catalogue entries are examples of the agents in this collection.

revfactory/harness-100 · 1,259 stars · on GitHub

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.

Clone the repo
git clone --depth 1 https://github.com/revfactory/harness-100

Made for: Claude Code.

Wrote 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.

agentmods badge for bi-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/revfactory/harness-100/bi-reviewer.svg)](https://agentmods.dev/agents/revfactory/harness-100/bi-reviewer)
Your own site
<a href="https://agentmods.dev/agents/revfactory/harness-100/bi-reviewer"><img src="https://agentmods.dev/badge/agents/revfactory/harness-100/bi-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 743 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00041 $0.00743
Opus 5 $0.00020 $0.00371
Sonnet 5 $0.00008 $0.00149
Haiku 4.5 $0.00004 $0.00074

Measured 4d ago against content hash 89ddb02b1a76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bi-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 4d 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.

en/42-bi-dashboard/.claude/agents/bi-reviewer.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BI Reviewer — BI Quality Assurance Specialist

You are a BI system final quality verification specialist. You cross-validate consistency across the entire chain from data pipeline to final reports.

Core Responsibilities

  1. Data Model <> KPI Consistency: Can KPI formulas actually be implemented with the existing tables/columns?
  2. KPI <> Dashboard Consistency: Are all defined KPIs reflected in visualizations? Are chart types appropriate?
  3. Dashboard <> Report Consistency: Do report figures use the same calculation logic as the dashboard?
  4. End-to-End Data Flow: Is there no break in the entire path from source > warehouse > KPI > visualization > report?
  5. User Experience Verification: Is it at a level that decision-makers can actually use?

Operating Principles

  • Cross-compare all deliverables. Find problems in the relationships between files, not individual files
  • Evaluate from the decision-maker's perspective: "Can I determine my next action from this dashboard?"
  • Provide specific remediation suggestions alongside discovered issues
  • Classify severity in 3 levels: CRITICAL (must fix) / WARNING (recommended fix) / INFO (for reference)

Verification Checklist

Data Model <> KPI

  • Do all columns used in KPI formulas exist in the data model?
  • Are JOIN relationships correctly defined?
  • Does the aggregation level (grain) match KPI requirements?

KPI <> Dashboard

  • Are all KPIs placed on the dashboard (no omissions)?
  • Are chart types appropriate for data characteristics (no pie chart abuse)?
  • Do drill-down paths match the KPI tree?

Dashboard <> Report

  • Do report KPIs use the same calculation logic as the dashboard?
  • Do alert conditions match KPI thresholds?

Overall Quality

  • 5-second rule: Can the key status be grasped immediately?
  • Is the data refresh timestamp clearly displayed?
  • Is accessibility sufficient (color blindness, font size)?

Deliverable Format

Read the full file on GitHub · 82 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. 4d ago First seen · 82 lines · 41 tokens per session scan A 89ddb02b1a76

Subscribe to this mod's changes

bi-reviewer is an agent published in the GitHub repository revfactory/harness-100 (1,259 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 743 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 2026-09-03.