From 41bf57d9ee00f18dbe412cb50fe14de319ae3f6b Mon Sep 17 00:00:00 2001 From: Florian BRUNIAUX Date: Mon, 12 Jan 2026 15:08:06 +0100 Subject: [PATCH] feat(audit): SSoT warning + incremental suggestions prompt Script: - needs_ssot_refactor flag: warns if CLAUDE.md >100 lines with 0 @refs - Red warning in human output suggesting SSoT pattern Prompt: - Focus on incremental improvements, not generic advice - Stricter health score (penalize missing SSoT) - Domain-specific quick wins only - Improve existing CLAUDE.md instead of full rewrite - Don't suggest duplicates of existing agents/commands Co-Authored-By: Claude Opus 4.5 --- CHANGELOG.md | 19 +++++++++++++++++++ README.md | 24 +++++++++++++----------- claude-code-reference.yaml | 2 +- english-ultimate-claude-code-guide.md | 4 ++-- examples/scripts/audit-scan.sh | 10 +++++++++- 5 files changed, 44 insertions(+), 15 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9f56a53..2030a36 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,6 +6,25 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/). ## [Unreleased] +## [2.9.9] - 2026-01-12 + +### Enhanced +- **audit-scan.sh** - SSoT refactor warning + - New `needs_ssot_refactor` flag: true if CLAUDE.md >100 lines with 0 @references + - Human output shows red warning suggesting SSoT pattern (split into @docs/) + - JSON output includes `needs_ssot_refactor` in quality section + +- **README.md** - Improved Full Audit prompt for incremental suggestions + - Added IMPORTANT instruction to focus on incremental improvements, not generic advice + - Health score now penalizes large CLAUDE.md without @refs + - Quick wins must be domain-specific, not generic + - If CLAUDE.md exists: suggest 3-5 improvements instead of full template + - Agents/commands suggestions must not duplicate existing ones + +### Stats +- 2 files modified +- Audit now provides targeted, incremental recommendations + ## [2.9.8] - 2026-01-12 ### Enhanced diff --git a/README.md b/README.md index c10bf48..94190e7 100644 --- a/README.md +++ b/README.md @@ -127,22 +127,24 @@ $CLAUDE_MD Local .claude/CLAUDE.md: $LOCAL_CLAUDE_MD -Based on ALL this context (tech stack, business domain, existing instructions), provide: +IMPORTANT: Focus on INCREMENTAL improvements to existing setup. Don't suggest creating things that already exist. If CLAUDE.md exists, suggest specific improvements to it rather than a full rewrite. + +Based on ALL this context, provide: 1. Stack Recap: runtime, framework, test runner, bundler, database, key integrations detected -2. Health Score (0-100) with priority breakdown -3. Findings table: Priority|Element|Status|Action -4. Top 3 quick wins (<5 min) tailored to THIS project's domain -5. CLAUDE.md template (~100 lines) that incorporates existing instructions + improvements -6. Suggested agents/commands/hooks specific to THIS project's business context -7. Ideas to leverage Claude Code for this specific domain and integrations" +2. Health Score (0-100) - be strict: penalize missing SSoT pattern if >100 lines without @refs +3. Findings table: Priority|Element|Status|Action (only gaps, not what exists) +4. Top 3 quick wins (<5 min) - MUST be specific to THIS project's domain (not generic advice) +5. If CLAUDE.md exists: list 3-5 specific improvements (not a full template). If missing: provide ~100 line template +6. Suggested agents/commands/hooks that DON'T duplicate existing ones - check extensions count first +7. Ideas to leverage Claude Code for this specific domain and detected integrations" ``` **What you get**: - **Stack recap**: Runtime, framework, test runner, bundler, database, and key integrations auto-detected -- Health score with prioritized findings -- Stack-specific CLAUDE.md template (~100 lines) that builds on your existing instructions +- Strict health score (penalizes large CLAUDE.md without @refs) +- **Incremental improvements**: Specific fixes for YOUR setup, not generic advice - Domain-aware suggestions (e.g., EdTech → session planning agents, E-commerce → inventory commands) -- Integration-aware ideas (e.g., Stripe → payment testing commands, Sentry → error monitoring hooks) +- Non-duplicate suggestions: Only recommends agents/commands you don't already have **Want maximum depth?** Use [claude-setup-audit-prompt.md](./claude-setup-audit-prompt.md) with `claude --ultrathink` @@ -385,7 +387,7 @@ If this guide saved you time, helped you master Claude Code, or inspired your wo --- -*Version 2.9.8 | January 2026 | Crafted with Claude* +*Version 2.9.9 | January 2026 | Crafted with Claude*