boost-settings — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited boost-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.
$ARGUMENTS is empty, call the boost_settings MCP tool with {"action": "get"} and display current settings using this format:⚙️ **ClaudeBoost Settings**
---
| Setting | Value | Options |
|---------|-------|---------|
| **Boost Level** | `{boost_level}` | `light` · `medium` · `full` |
| **Auto Boost** | `{auto_boost}` | `true` · `false` |
---
**Levels:**
- **light** — Clarify + structure only. Minimal changes.
- **medium** — Add structure, constraints, brief verification. Balanced.
- **full** — Full enterprise playbook with anti-patterns, metrics, detailed criteria.
**Usage:**
`/boost-settings --level light`
`/boost-settings --auto false`$ARGUMENTS contains flags, parse them:--level light or --level medium or --level full or -l light or -l medium or -l full → call boost_settings with {"action": "set", "boost_level": "..."}--auto true or --auto false or -a true or -a false → call boost_settings with {"action": "set", "auto_boost": true/false}level light, auto false✅ **Updated:** {setting} → {new_value}``/mcp to check status."~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.