/fewer-permission-prompts

Scans your own transcripts for common read-only Bash and MCP tool calls and adds a prioritized allowlist to the project-wide .claude/settings.json to reduce permission prompts.

Scans your own transcripts for common read-only Bash and MCP tool calls and adds a prioritized allowlist to the project-wide .claude/settings.json to reduce permission prompts. [Skill]

✅ WHEN TO USE IT?

Auto-allow recurring, harmless read-only commands after a few sessions

/fewer-permission-prompts after several sessions full of repeated permission prompts for git status, ls, etc.

Generate a sensible allowlist baseline for team onboarding

/fewer-permission-prompts to pre-populate .claude/settings.json with common read-only calls

⛔ WHEN NOT TO?

Wanting to blanket-allow write/risky commands too, without prompts

the skill specifically scans for common read-only Bash/MCP calls, not write commands

Better: keep allowing write/risky commands manually and deliberately in .claude/settings.json (e.g. via the update-config skill)

SOURCES

Claude Code Doku (offiziell) ↗ code.claude.com