Manages settings for Claude Code (JSON) and Codex CLI (TOML) coding agents, including permissions, sandbox, model selection, profiles, env vars, and hooks.
npx claudepluginhub codealive-ai/agents-reflection-skillsThis skill uses the workspace's default tool permissions.
Manage configuration for coding agents.
Manages settings for Claude Code, Codex CLI, OpenCode: views files, configures models, permissions, sandbox, hooks, env vars, profiles. Restart agent after edits.
Manages Claude Code settings including settings.json (user/project/enterprise), permissions, sandbox, plugins, env vars, and tools via docs-management delegation. For config setup and troubleshooting.
Explains Claude Code settings hierarchy, permission wildcards, allow/deny patterns, and tool configurations. Use for setting up project permissions, debugging access issues, or understanding tool blocks.
Share bugs, ideas, or general feedback.
Manage configuration for coding agents.
IMPORTANT: After modifying settings, always inform the user that they need to restart the agent for changes to take effect. Most settings are only loaded at startup.
| Scope | Location | Shared with team? |
|---|---|---|
| User | ~/.claude/settings.json | No |
| Project | .claude/settings.json | Yes (committed) |
| Local | .claude/settings.local.json | No (gitignored) |
| Managed | System-level managed-settings.json | IT-deployed |
Precedence (highest to lowest): Managed → Command line → Local → Project → User
cat ~/.claude/settings.json 2>/dev/null || echo "No user settings"
cat .claude/settings.json 2>/dev/null || echo "No project settings"
cat .claude/settings.local.json 2>/dev/null || echo "No local settings"
Use the Edit or Write tool to modify settings files. Always read existing content first to merge changes.
{
"model": "claude-sonnet-4-5-20250929"
}
{
"permissions": {
"allow": ["Bash(npm run:*)", "Bash(git:*)"],
"deny": ["Read(.env)", "Read(.env.*)", "WebFetch"],
"defaultMode": "allowEdits"
}
}
{
"env": {
"MY_VAR": "value",
"CLAUDE_CODE_ENABLE_TELEMETRY": "1"
}
}
{
"alwaysThinkingEnabled": true
}
{
"attribution": {
"commit": "Generated with AI\n\nCo-Authored-By: AI <ai@example.com>",
"pr": ""
}
}
{
"sandbox": {
"enabled": true,
"autoAllowBashIfSandboxed": true,
"excludedCommands": ["docker", "git"]
}
}
{
"hooks": {
"PreToolUse": {
"Bash": "echo 'Running command...'"
}
}
}
~/.claude/settings.json): Personal preferences across all projects.claude/settings.json): Team-shared settings, commit to git.claude/settings.local.json): Personal project overrides, not committedCodex uses TOML format in ~/.codex/config.toml (user) and .codex/config.toml (project).
model = "gpt-5.2-codex"
approval_policy = "on-request" # untrusted | on-failure | on-request | never
sandbox_mode = "workspace-write" # read-only | workspace-write | danger-full-access
Key differences from Claude Code:
.codex/rules/)codex features list)See references/codex-settings.md for full Codex config reference.