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

docs: factual audit + reference sync — 260 findings corrected

Browse source 
Parallel 6-agent audit against official Anthropic docs (llms-full.txt).
Key corrections applied across permissions, hooks, MCP, security, privacy, reference.yaml.

Highlights:
- Fix MCP config path (~/.claude.json), mcpServers key, variable substitution syntax
- Fix permission modes (5 not 3), :* syntax (×6), Stop event description
- Fix hook JSON field names (hook_event_name, tool_name, tool_input, session_id)
- Fix filesystem restriction docs (permission rules, not settings.json keys)
- Fix data-privacy: 4-tier retention, /bug 5yr warning, ZDR conditions, 5 telemetry opt-out vars
- Add official llms.txt/llms-full.txt references to CLAUDE.md + machine-readable/llms.txt
- Reference.yaml: 375 entries re-synced (92% had wrong line numbers — guide grew 15K→21K lines)
- New script: scripts/resync-reference-yaml.py for automated line number sync
- Quiz: corrected answers for hooks (07), memory settings (03), MCP servers (08)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Florian BRUNIAUX 2026-02-26 12:10:14 +01:00
parent ad735dfff4
commit 8e63d84b47
26 changed files with 1125 additions and 566 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/hooks/bash/learning-capture.sh
View file

@ -1,6 +1,6 @@
#!/bin/bash
# Hook: Stop - Capture one learning insight at session end
# Event: Stop (when user ends session or interrupts)
# Event: Stop (when Claude finishes responding)
# Purpose: Build a learning journal with minimal friction
#
# Exit codes:

10
examples/hooks/bash/mcp-config-integrity.sh
View file

@ -6,7 +6,7 @@
# Purpose: Verify MCP configuration has not been tampered with
#
# This hook addresses CVE-2025-54135 and CVE-2025-54136 by:
# - Computing hash of ~/.claude/mcp.json
# - Computing hash of ~/.claude.json (MCP config location)
# - Comparing against stored baseline
# - Alerting on unauthorized modifications
# - Checking project-level .mcp.json for suspicious content
@ -22,7 +22,7 @@
# }
#
# Initial setup (run once to create baseline):
# sha256sum ~/.claude/mcp.json > ~/.claude/.mcp-baseline.sha256
# sha256sum ~/.claude.json > ~/.claude/.mcp-baseline.sha256
#
# Exit codes:
# 0 = allow (config unchanged or no baseline)
@ -36,7 +36,7 @@
set -euo pipefail
# Configuration paths
MCP_CONFIG="${HOME}/.claude/mcp.json"
MCP_CONFIG="${HOME}/.claude.json"
MCP_BASELINE="${HOME}/.claude/.mcp-baseline.sha256"
PROJECT_MCP=".mcp.json"
@ -51,11 +51,11 @@ if [[ -f "$MCP_CONFIG" ]]; then
BASELINE_HASH=$(awk '{print $1}' "$MCP_BASELINE" 2>/dev/null || echo "")
if [[ -n "$CURRENT_HASH" && -n "$BASELINE_HASH" && "$CURRENT_HASH" != "$BASELINE_HASH" ]]; then
WARNINGS+=("MCP config modified since baseline was created. Review ~/.claude/mcp.json for unauthorized changes. Run 'sha256sum ~/.claude/mcp.json > ~/.claude/.mcp-baseline.sha256' to update baseline if changes are legitimate.")
WARNINGS+=("MCP config modified since baseline was created. Review ~/.claude.json for unauthorized changes. Run 'sha256sum ~/.claude.json > ~/.claude/.mcp-baseline.sha256' to update baseline if changes are legitimate.")
fi
else
# No baseline - suggest creating one
WARNINGS+=("No MCP config baseline found. Consider running: sha256sum ~/.claude/mcp.json > ~/.claude/.mcp-baseline.sha256")
WARNINGS+=("No MCP config baseline found. Consider running: sha256sum ~/.claude.json > ~/.claude/.mcp-baseline.sha256")
fi
# === CHECK FOR SUSPICIOUS MCP SERVERS ===