From harness-engineering
Production safety guard that blocks destructive commands for the session. Use when user says '/careful', 'production work', or 'cautious mode'. Do NOT activate for local development work. Deactivate with '/careful off'.
npx claudepluginhub toru-oizumi/claude-harness-engineering --plugin harness-engineeringThis skill uses the workspace's default tool permissions.
A session-scoped safety guard that blocks destructive commands via PreToolUse hook. Activate before production operations; deactivates at session end or on explicit `/careful off`.
Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.
A session-scoped safety guard that blocks destructive commands via PreToolUse hook. Activate before production operations; deactivates at session end or on explicit /careful off.
When this skill is triggered:
mkdir -p .claude && touch .claude/careful-mode-active
rm -rf (wildcard deletion)DROP TABLE, DROP DATABASEgit push --force, git push -fkubectl deleteterraform destroyWhen user says /careful off or deactivates:
rm -f .claude/careful-mode-active
The hooks/careful-guard.js PreToolUse hook intercepts every Bash tool call and blocks if:
.claude/careful-mode-active existsBlocked commands show a warning and require explicit user override.
If a blocked command truly needs to run, user can:
/careful off/carefulSee gotchas.md in this directory for known pitfalls and recurring mistakes when using this skill.