claude-hooks-settings — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited claude-hooks-settings (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Bundled commands use $PLUGIN_ROOT ($env:PLUGIN_ROOT in PowerShell; same path suffix) for the plugin root. Set it once: use the host's plugin-root variable when defined (Claude Code: PLUGIN_ROOT="$CLAUDE_PLUGIN_ROOT"), otherwise the absolute path of this plugin's root directory.
Use this skill for Claude Code settings and customization work: settings JSON, hooks, CLAUDE.md or rules loading, custom agents, tool allow/deny rules, output styles, workflows, setting sources, plugin-provided customizations, safe-mode comparisons, and bare-mode explicit context.
Read $PLUGIN_ROOT/references/hooks-settings.md for hook lifecycle, setting-source boundaries, and safety details.
Inspect the target files and scope before editing:
Use CLI evidence when behavior differs from expectation:
python3 "$PLUGIN_ROOT/scripts/claude_code_inspector.py" --commands auto-mode --json
claude auto-mode config
claude auto-mode defaultsUse hooks only when deterministic lifecycle automation is needed. Prefer narrow events and matchers:
PreToolUse, PermissionRequest, PermissionDenied;PostToolUse, PostToolUseFailure, PostToolBatch;SessionStart, SessionEnd;WorktreeCreate, WorktreeRemove;ConfigChange, InstructionsLoaded.Keep hook scripts deterministic, reviewable, and low-output. Do not log full prompts, secrets, or broad environment dumps.
Use --tools, --allowedTools, and --disallowedTools for runtime scope:
claude --tools "Read,Grep,Glob"
claude --allowedTools "Bash(git *) Edit"
claude --disallowedTools "Bash(rm *)"For durable rules, edit the appropriate settings file after confirming scope. Do not use hooks as the only enforcement mechanism for high-risk actions.
Before editing:
When troubleshooting, compare normal startup with --safe-mode and --bare before deleting customizations.
Report the setting scope, files changed, hook events/matchers/rules, validation command, safe-mode or bare-mode comparison when used, and any residual risk.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.