Audits and consolidates agent permissions to maintain security and consistency across project environments.

Install

mkdir -p .claude/skills/tidy-perms && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/18123" && unzip -o skill.zip -d .claude/skills/tidy-perms && rm skill.zip

Installs to .claude/skills/tidy-perms

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Consolidate accumulated permission grants across Claude Code, Codex, and Gemini: move trusted commands into project settings, clean garbage entries, verify cross-agent consistency, commit project-level configs.
210 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Categorize Claude local permissions
  • Move project-safe rules to project settings
  • Validate JSON files with jq -e
  • Report cross-agent trust/MCP parity
  • Commit only .claude/settings.json if changed

How it works

The skill reads Claude project and local settings, discovers project CLIs, and categorizes entries in settings.local.json. It then merges project-safe entries into project settings and rewrites local settings with only personal entries.

Inputs & outputs

You give it
Claude Code settings (.claude/settings.json, .claude/settings.local.json), Codex CLI config (~/.codex/config.toml), Gemini CLI settings (~/.gemini/settings.json
You get back
Updated .claude/settings.json, rewritten .claude/settings.local.json, report of cross-agent trust/MCP parity

When to use tidy-perms

  • Consolidate tool permissions
  • Audit agent access rules
  • Clean up duplicate config entries
  • Secure project-level environment settings

About this skill

Permissions Consolidation

Route to consolidate or audit; read the file in the Read column before acting. Keep unclear entries PERSONAL and ask; never weaken safety.

Actions

ActionTriggerRead
consolidatedefault/tidy permissionsreferences/consolidate.md
auditaudit/review permissionsreferences/audit.md
helphelp/list actionsthis table

Rules

  • Never git add -A; stage explicit project config paths only.
  • Never commit settings.local.json, ~/.codex/config.toml, or ~/.gemini/*.json.
  • Never remove hooks or unrelated keys, or add force-push/reset/clean/rm rules to allowlists.

When not to use it

  • Adding git push --force to project allowlists
  • Adding git reset --hard to project allowlists
  • Adding rm -rf to project allowlists

Limitations

  • Never commits settings.local.json
  • Never commits ~/.codex/config.toml
  • Never commits ~/.gemini/*.json

How it compares

This skill automates the consolidation of scattered permission grants into project settings, ensuring consistency and security across multiple coding agents, which differs from manual configuration that can lead to inconsistencies.

Compared to similar skills

tidy-perms side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
tidy-perms (this skill)029dNo flagsIntermediate
skill-install46moReviewIntermediate
google-workspace-cli91moReviewAdvanced
context-engine21moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

skill-install

cexll

Install Claude skills from GitHub repositories with automated security scanning. Triggers when users want to install skills from a GitHub URL, need to browse available skills in a repository, or want to safely add new skills to their Claude environment.

450

google-workspace-cli

alirezarezvani

Google Workspace administration via the gws CLI. Install, authenticate, and automate Gmail, Drive, Sheets, Calendar, Docs, Chat, and Tasks. Run security audits, execute 43 built-in recipes, and use 10 persona bundles. Use for Google Workspace admin, gws CLI setup, Gmail automation, Drive management, or Calendar scheduling.

916

context-engine

alirezarezvani

Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (>90 days), enriches context during conversations, and enforces privacy/anonymization rules before external API calls.

21

aif

hightemp

Set up agent context for a project. Analyzes tech stack, installs relevant skills from skills.sh, generates custom skills, and configures MCP servers. Use when starting new project, setting up AI context, or asking "set up project", "configure AI", "what skills do I need".

00

windows-ui-automation

martinholovsky

Expert in Windows UI Automation (UIA) and Win32 APIs for desktop automation. Specializes in accessible, secure automation of Windows applications including element discovery, input simulation, and process interaction. HIGH-RISK skill requiring strict security controls for system access.

17126

1password

openclaw

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

2799

Search skills

Search the agent skills registry