What is analyzeRepo CLAUDE.md?

Project instructions for analyzeRepo, a Go command-line tool that examines GitHub repositories or local code and creates onboarding and analysis documents. A command-line tool is a program operated through a terminal.

Use them when changing repository discovery, file analysis, statistics, configuration, command-line behavior, or the generated ANALYSIS.md, ONBOARDING.md, and CLAUDE.md files.

They keep changes consistent with the tool's five-stage analysis process, its Go project structure, and its two ways of calling Claude.

How rlnorthcutt/analyzeRepo configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to rlnorthcutt/analyzeRepo. 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/rlnorthcutt/analyzeRepo/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/rlnorthcutt/analyzeRepo

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/rlnorthcutt/analyzerepo/claude-md/github.svg)](https://agentmods.dev/instructions/rlnorthcutt/analyzerepo/claude-md)

Your own site

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

Per session 1,112 This file is loaded in full into every session.

When invoked 1,112 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	$0.01112	$0.01112
Opus 5.5	$0.00445	$0.00445
Sonnet 5.5	$0.00222	$0.00222
Haiku 4.5	$0.00111	$0.00111

Measured 2mo ago against content hash 8abf7e75f96d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

analyzeRepo 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 · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

analyzeRepo

A Go CLI tool that analyzes GitHub repositories or local codebases using Claude AI to generate onboarding guides, per-file analysis with improvement suggestions, and CLAUDE.md context files.

Architecture

The tool is structured as a standard Go CLI application using Cobra, with all business logic in internal/ packages:

cmd/root.go wires together all packages, resolves config (interactive wizard or flags), and drives the analysis pipeline through five sequential phases: discovery, key file selection, per-file analysis, stats, and report writing.
internal/analyze is the AI layer. It contains a dual-backend Client that uses the Anthropic SDK when ANTHROPIC_API_KEY is set, falling back to the claude CLI subprocess. Token usage is tracked atomically across concurrent goroutines.
internal/fetch is the ingestion layer. It clones GitHub repos or resolves local paths, walks the file tree filtering ignored/binary files, and renders a directory tree string.
internal/report is the output layer. Pure writer functions take structured data and produce ANALYSIS.md, ONBOARDING.md, and CLAUDE.md files.
internal/stats computes per-language file and line counts from the file list.
internal/tui contains two Bubble Tea models: a multi-step wizard for interactive config collection (wizard.go) and a live progress pipeline view with a scrollable results panel (pipeline.go).

Directory Structure

main.go                  # Minimal bootstrap; calls cmd.Execute()
cmd/
  root.go                # Cobra command, flag parsing, pipeline orchestration
  root_test.go
internal/
  analyze/
    analyze.go           # Claude AI client, dual-backend, per-file & report prompts
    analyze_test.go
  fetch/
    fetch.go             # Repo cloning, file tree walking, binary detection
    fetch_test.go
  report/
    report.go            # Markdown report writers (ANALYSIS.md, ONBOARDING.md, CLAUDE.md)
    report_test.go
  stats/
    stats.go             # Language detection and line counting
    stats_test.go
  tui/
    pipeline.go          # Bubble Tea model for live analysis progress
    pipeline_test.go
    wizard.go            # Bubble Tea multi-step config wizard
go.mod
go.sum

Read the full file on GitHub · 89 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 · 89 lines · 1,112 tokens per session scan A 8abf7e75f96d

Subscribe to this mod's changes

analyzeRepo CLAUDE.md is an instructions file published in the GitHub repository rlnorthcutt/analyzeRepo (23 stars, last pushed 8mo ago), licensed MIT. It adds 1,112 tokens to every session, about $0.0044 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 2026-08-30.

analyzeRepo CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
analyzeRepo CLAUDE.mdrlnorthcutt/analyzeRepo	Instructions file	23	8mo ago	MIT	A	1,112	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

analyzeRepo: Instructions file for Claude Code