Settings Management

What it does

When your agent uses it

• Tasks that involve Subagents

Example prompts

• “/settings-management”

Requirements

• Docker

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Determine scope: Ask user which scope (user/project/local) if not specified
2. 2Read existing settings: Always read current file before modifying
3. 3Merge changes: Preserve existing settings, only modify requested keys
4. 4Validate JSON: Ensure valid JSON before writing
5. 5Confirm changes: Show user the final settings
6. 6Remind to restart: Tell user to restart Claude Code for changes to take effect

What it can do on your machine

Read from SKILL.md and the folder at commit 4cfeb10. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • codex

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • opencode.ai

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Settings Management loads about 1.9k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 86 tokens; SKILL.md has 511 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~86

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~12k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:56

  "deny": ["Read(.env)", "Read(.env.*)", "WebFetch"],

• NoteMentions a .env fileSKILL.md:195

  "ask": ["Write(**/.env*)"]

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from CodeAlive-AI/ai-driven-development at commit 4cfeb10, republished under its MIT licence (© CodeAlive-AI). 511 words, ~1,858 tokens.

name

settings-management

description

View and configure settings for coding agents (Claude Code, Codex CLI, OpenCode, Devin CLI/Desktop, and others). Covers JSON settings for Claude Code and Devin, TOML for Codex CLI, and JSON/JSONC for OpenCode, including permissions, sandbox, model selection, profiles, feature flags, providers, hooks, subagents, and skills.

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"

{
  "model": "claude-opus-4-7",
  "effort": "high"
}

{
  "permissions": {
    "allow": ["Bash(npm run:*)", "Bash(git:*)"],
    "deny": ["Read(.env)", "Read(.env.*)", "WebFetch"],
    "defaultMode": "acceptEdits"
  }
}

{
  "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...'"
    }
  }
}

model = "gpt-5.5"                  # As of April 2026; gpt-5.4 is a valid fallback
approval_policy = "on-request"     # untrusted | on-request | never (or { granular = { ... } })
                                    # NOTE: "on-failure" is DEPRECATED — migrate to on-request or never
sandbox_mode = "workspace-write"   # read-only | workspace-write | danger-full-access

[features]
codex_hooks = true                 # Lifecycle hooks (stable in v0.124, April 2026)
multi_agent = true                 # Subagent orchestration (GA March 2026)

{
  "$schema": "https://opencode.ai/config.json",
  "model": "anthropic/claude-sonnet-4-5",
  "permission": {
    "edit": "ask",
    "bash": { "*": "ask", "git status *": "allow" }
  },
  "instructions": ["AGENTS.md", "docs/style.md"]
}

{
  "agent": { "model": "swe-2-high" },
  "permissions": {
    "allow": ["Read(**)", "Exec(git)"],
    "ask": ["Write(**/.env*)"]
  },
  "read_config_from": { "claude": true, "cursor": true, "windsurf": true }
}

© CodeAlive-AI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in skills/settings-management of CodeAlive-AI/ai-driven-development.

• SKILL.md
• references/claude-settings.md
• references/codex-settings.md
• references/devin-settings.md
• references/opencode-settings.md

Open the folder on GitHubat commit 4cfeb10