marketing-shibata50/claude-code-ultimate-guide
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

feat(deep-audit): context-aware analysis with privacy notice

Browse source 
- Full Audit now reads README.md, CLAUDE.md, .claude/CLAUDE.md
- Claude analyzes business domain for tailored recommendations
- Domain-specific suggestions (EdTech, E-commerce, etc.)
- Added privacy notice: all data stays local, nothing sent to repo

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Florian BRUNIAUX 2026-01-12 14:39:04 +01:00
parent 98044a0a47
commit 34235a7283
4 changed files with 47 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

13
CHANGELOG.md
View file

@ -6,6 +6,19 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
## [Unreleased]
## [2.9.7] - 2026-01-12
### Enhanced
- **README.md** - Deep Audit now context-aware
- Full Audit command now reads project's README.md, CLAUDE.md, and .claude/CLAUDE.md
- Claude analyzes business domain to provide tailored recommendations
- Domain-specific suggestions (EdTech → session agents, E-commerce → inventory commands)
- Privacy notice: all data stays local, nothing sent back to repo
### Stats
- 1 file modified (README.md)
- Deep Audit now provides personalized, domain-aware recommendations
## [2.9.6] - 2026-01-12
### Fixed

41
README.md
View file

@ -93,33 +93,54 @@ curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-
### 🔬 Deep Audit (Personalized Recommendations)
Get a comprehensive audit with health score, prioritized findings, and custom templates for your project:
Get a comprehensive, **context-aware** audit that analyzes your project's README, CLAUDE.md files, and business domain to provide tailored recommendations:
> 🔒 **Privacy**: Everything runs locally on your machine. The script only downloads reference files from this repo—your project files (README, CLAUDE.md) are read locally and sent only to your own Claude CLI. Nothing is sent back to this repository or any third party.
**Quick Version** (~10 sec):
```bash
curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/examples/scripts/audit-scan.sh | bash -s -- --json | claude -p "Analyze this Claude Code setup. Give: 1) Health score 0-100 2) Top 3 quick wins 3) CLAUDE.md template for detected stack. Be concise."
```
**Full Audit** (~30 sec, recommended):
**Full Audit with Context** (~30 sec, recommended):
```bash
# Copy entire block
# Claude Code Deep Audit - Context-Aware Version
# Downloads reference files, reads YOUR local files, analyzes with Claude
REF=$(curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/claude-code-reference.yaml)
SCAN=$(curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/examples/scripts/audit-scan.sh | bash -s -- --json 2>/dev/null)
README_CONTENT=$(head -100 README.md 2>/dev/null || echo "No README.md found")
CLAUDE_MD=$(cat CLAUDE.md 2>/dev/null || echo "No CLAUDE.md found")
LOCAL_CLAUDE_MD=$(cat .claude/CLAUDE.md 2>/dev/null || echo "No .claude/CLAUDE.md found")
claude -p "Reference:
$REF
My setup:
Scan results:
$SCAN
Audit my Claude Code setup. Output:
Project README (first 100 lines):
$README_CONTENT
Project CLAUDE.md:
$CLAUDE_MD
Local .claude/CLAUDE.md:
$LOCAL_CLAUDE_MD
Based on ALL this context (tech stack, business domain, existing instructions), provide:
1. Health Score (0-100) with priority breakdown
2. Findings table: Priority|Element|Status|Action
3. Top 3 quick wins (<5 min)
4. CLAUDE.md template (~60 lines) for my stack
5. Suggested agents/commands/hooks for my project type"
3. Top 3 quick wins (<5 min) tailored to THIS project's domain
4. CLAUDE.md template (~60 lines) that incorporates existing instructions + improvements
5. Suggested agents/commands/hooks specific to THIS project's business context
6. Ideas to leverage Claude Code for this specific domain"
```
**What you get**: Health score, prioritized findings, stack-specific CLAUDE.md template, suggested extensions
**What you get**:
- Health score with prioritized findings
- Stack-specific CLAUDE.md template that builds on your existing instructions
- Domain-aware suggestions (e.g., EdTech → session planning agents, E-commerce → inventory commands)
- Custom agents/commands/hooks ideas tailored to your project
**Want maximum depth?** Use [claude-setup-audit-prompt.md](./claude-setup-audit-prompt.md) with `claude --ultrathink`
@ -362,7 +383,7 @@ If this guide saved you time, helped you master Claude Code, or inspired your wo
---
*Version 2.9.6 | January 2026 | Crafted with Claude*
*Version 2.9.7 | January 2026 | Crafted with Claude*
<!-- SEO Keywords -->
<!-- claude code, claude code tutorial, anthropic cli, ai coding assistant, claude code mcp,

2
claude-code-reference.yaml
View file

@ -3,7 +3,7 @@
# Source: english-ultimate-claude-code-guide.md
# Purpose: Condensed index for LLMs to quickly answer user questions about Claude Code
version: "2.9.6"
version: "2.9.7"
updated: "2026-01"
# ════════════════════════════════════════════════════════════════

4
english-ultimate-claude-code-guide.md
View file

@ -10,7 +10,7 @@
**Last updated**: January 2026
**Version**: 2.9.6
**Version**: 2.9.7
---
@ -9009,4 +9009,4 @@ Thumbs.db
**Contributions**: Issues and PRs welcome.
**Last updated**: January 2026 | **Version**: 2.9.6
**Last updated**: January 2026 | **Version**: 2.9.7