Set tool permissions for Claude Code. Configures allowed commands, rules, and preferences in .claude/ directory. Triggers on: setperms, init tools, configure permissions, setup project, set permissions, init claude.
86
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Core Claude Code environment initialization
Settings file location
0%
100%
Rules file location
0%
100%
Modern search tools allowed
100%
100%
Modern file tools allowed
50%
100%
Data processing tools allowed
28%
100%
AI CLI tools allowed
0%
100%
Git safety ask list
0%
100%
Empty deny list
0%
100%
Empty hooks object
0%
100%
Tool substitution table in rules
0%
100%
Python tool preference in rules
0%
100%
Web fetching priority in rules
0%
100%
Task runner preference in rules
0%
100%
Git safety guidance in rules
0%
100%
Without context: $0.2863 · 1m 32s · 15 turns · 18 in / 4,900 out tokens
With context: $0.5141 · 1m 56s · 23 turns · 28 in / 6,660 out tokens
Full cloud/container tool permissions
Container tools allowed
100%
100%
Kubernetes tools allowed
100%
100%
IaC tools allowed
100%
100%
PaaS/edge tools allowed
0%
100%
Base dev tools retained
30%
100%
AI CLI tools retained
0%
100%
Git safety ask list retained
0%
100%
Rules file created
0%
100%
Settings file location
0%
100%
Correct file structure
50%
100%
Without context: $0.1480 · 49s · 11 turns · 16 in / 2,501 out tokens
With context: $0.5200 · 2m 3s · 25 turns · 64 in / 6,493 out tokens
Selective permissions-only installation
Settings file created
25%
100%
Existing rules preserved
100%
100%
Modern search tools in permissions
0%
100%
Modern file tools in permissions
0%
100%
Data processing tools in permissions
0%
100%
AI CLI tools in permissions
0%
100%
Git safety ask list
0%
100%
Git tools allowed
50%
100%
Empty deny list
100%
100%
Project-local placement
50%
100%
Analysis tools allowed
0%
100%
uv package manager allowed
0%
100%
Without context: $0.3690 · 1m 25s · 21 turns · 27 in / 4,976 out tokens
With context: $0.4974 · 1m 44s · 25 turns · 71 in / 5,820 out tokens
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.