What is reportforge CLAUDE.md?

A set of Claude Code instructions for ReportForge PBI, a local application that turns CSV data into Power BI report files. Power BI is Microsoft's tool for building interactive data dashboards, and CSV is a plain-text table format.

Use it to generate Power BI .pbit templates from local or pasted CSV data, identify useful measures and dimensions, and save reports in the project's output folder.

It defines the supported local workflow and explains how to profile CSV data, build report components, and save generated files without depending on a remote deployment.

How twilize5/reportforge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to twilize5/reportforge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/twilize5/reportforge/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/twilize5/reportforge

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/twilize5/reportforge/claude-md/github.svg)](https://agentmods.dev/instructions/twilize5/reportforge/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/twilize5/reportforge/claude-md"><img src="https://agentmods.dev/badge/instructions/twilize5/reportforge/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/twilize5/reportforge/claude-md"><img src="https://agentmods.dev/badge/instructions/twilize5/reportforge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 551 This file is loaded in full into every session.

When invoked 551 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00551	$0.00551
Opus 5.5	$0.00220	$0.00220
Sonnet 5.5	$0.00110	$0.00110
Haiku 4.5	$0.00055	$0.00055

Measured 2mo ago against content hash 2d451dbaa59f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reportforge CLAUDE.md 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.

CLAUDE.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ReportForge PBI

ReportForge PBI is a local-first Claude Desktop MCP app for generating Power BI .pbit reports.

Supported Setup

Railway deployment is not the current target. The intended workflow is:

Clone or download this repo locally.
Run setup_local.ps1.
Configure Claude Desktop to launch run_mcp_stdio.ps1.
Use Claude Desktop MCP tools to read local CSV files and save reports locally.

Capabilities

Generate Power BI dashboards from local CSV files.
Generate from pasted CSV text or base64 CSV.
Profile CSVs for measures, dimensions, temporal columns, geographic columns, KPI candidates, and domain hints.
Build semantic model JSON, Power Query M, Power BI layout JSON, theme JSON, and compiled .pbit files.
Export local .pbit files into generated_reports/.
Shorten generated filenames to avoid Windows/Power BI path errors.
Apply template-based dashboard layouts:
- KPI rail
- KPI grid
- central chart slots
- right-side filter panel
- light canvas
- white cards
- subtle borders
- capped visual counts to avoid clutter
Strip problematic generated sort metadata that caused Power BI Desktop 2026 renderer failures.
Do not emit hasDefaultSort, OrderBy, Sort, or sortDefinitions in generated visual configs.

Anthropic API Usage

No Anthropic key is required for deterministic CSV-to-dashboard tools:

create_dashboard
create_from_csv_file_path
create_from_csv_text
create_from_csv
export_pbit_file
get_report_state

An Anthropic key is required for server-side LLM features:

create_report
add_visual
edit_styling
apply_image_theme
add_filter

In Claude Desktop local mode, put ANTHROPIC_API_KEY in the MCP server env block or set it as a normal Windows environment variable.

Important Files

LOCAL_SETUP.md - complete local install and Claude Desktop config.
setup_local.ps1 - creates venv and installs Python requirements.
run_mcp_stdio.ps1 - Claude Desktop stdio entrypoint.
run_api.ps1 - optional local FastAPI entrypoint.
mcp_server.py - MCP tool definitions.
auto_intent.py - deterministic CSV dashboard generation.
file_writer.py - Power BI project and PBIT writer.
prompts/ - prompt files for Anthropic-powered features.

Read the full file on GitHub · 71 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.

2mo ago First seen · 71 lines · 551 tokens per session scan A 2d451dbaa59f

Subscribe to this mod's changes

reportforge CLAUDE.md is an instructions file published in the GitHub repository twilize5/reportforge (0 stars, last pushed 5mo ago), licensed MIT. It adds 551 tokens to every session, about $0.0022 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.

Analytics and metrics

reportforge CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
reportforge CLAUDE.mdtwilize5/reportforge	Instructions file	0	5mo ago	MIT	A	551	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

reportforge: Instructions file for Claude Code