More screenshots
Works with the AI Agents you already use
Claude Code Settings Check
This skill finds those and ten other Claude Code settings mistakes before you commit or trust the settings, and tells you how to fix each one.
$5
Claude Code Settings Check
Example session with this skill installed
Check this project with code-agent-settings-check.
- Read your context and instructions
- Compiled the claude code settings
$ python3 scripts/check_claude_settings.py examples/risky
BLOCK .claude/settings.json:4 CC01 BYPASS_PERMISSIONS_MODE
"defaultMode": "bypassPermissions",
Why: permissions.defaultMode is bypassPermissions, so sessions start with permission prompts skipped: shell commands, file edits, network requests and writes to .git and .claude run without asking, and deny rules are the only check left. Claude Code's recent versions ignore it in project and local settings, but older versions apply it to everyone who opens the project, and in user or managed settings it applies to every session.
Safer: Use default, acceptEdits or plan with specific allow rules. Keep bypassPermissions for throwaway containers or VMs, and set permissions.disableBypassPermissionsMode to "disable" in managed settings so nobody turns it on by accident.
BLOCK .claude/settings.json:7 CC02 ALLOW_RULE_RUNS_ANY_COMMAND
BLOCK .claude/settings.json:8 CC02 ALLOW_RULE_RUNS_ANY_COMMAND
BLOCK .claude/settings.json:9 CC03 NETWORK_COMMAND_ALLOWED
BLOCK .claude/settings.json:19 CC04 SECRET_IN_SETTINGS
REVIEW .claude/settings.json:10 CC14 BROAD_FILE_ACCESS
REVIEW .claude/settings.json:11 CC16 WEBFETCH_ANY_DOMAIN
REVIEW .claude/settings.json:13 CC15 ENV_FILE_NOT_DENIED
REVIEW .claude/settings.json:14 CC18 RULE_DOES_NOT_MATCH
REVIEW .claude/settings.json:25 CC11 HOOK_DOWNLOADS_OR_SENDS_DATA
REVIEW .claude/settings.json:33 CC12 HOOK_RUNS_TOOL_INPUT
REVIEW .claude/settings.json:41 CC11 HOOK_DOWNLOADS_OR_SENDS_DATA
REVIEW .claude/settings.json:49 CC17 SANDBOX_WEAKENED
REVIEW .claude/settings.local.json:5 CC14 BROAD_FILE_ACCESS
REVIEW .claude/settings.local.json:8 CC13 ALL_PROJECT_MCP_SERVERS_APPROVED
(Each finding also has Why and Safer lines, as in the first one.)
Verdict: BLOCK. Checked 2 files, 2 with Claude Code settings content.
This is a static check of file text. NOT FLAGGED is not a guarantee.
Connects securely to your tools. The creator never sees your data.
About this skill
"Bash(python3:*)" in a committed .claude/settings.json lets any text Claude reads get code run on your teammates' machines without a prompt, and a SessionStart hook with curl | bash runs a remote script every time someone opens the project. This skill finds those and ten other Claude Code settings mistakes before you commit or trust the settings, and tells you how to fix each one.
Your agent runs a scanner on .claude/settings.json and .claude/settings.local.json in each project folder, on ~/.claude/settings.json when you point it there, and on managed-settings.json files. It follows Claude Code's own rule syntax: Bash(npm run ) and Bash(npm run:) are the same prefix rule, //path is absolute while /path stays inside the project, only Read and Edit rules match paths, and an allow rule of * approves nothing. It reads hook commands and HTTP hooks, helper commands such as apiKeyHelper, and sandbox settings, and lists the .env files beside each .claude folder. It never runs Claude Code, hooks or MCP servers. It returns BLOCK, REVIEW, or NOT FLAGGED, with the file, line, reason, and a safer approach. Secrets are never printed.
What it checks
BLOCK
- CC01: defaultMode set to bypassPermissions
- CC02: allow rules that approve any command (Bash, Bash(), Bash(python:), Bash(npx *), Bash(git *))
- CC03: curl, wget, scp, ssh, gh api or gh gist create allowed with any arguments
- CC04: keys and tokens in env, apiKeyHelper, hook commands or HTTP hook headers
REVIEW
- CC11: hooks that download and run code or send data to outside servers
- CC12: hooks that eval their tool input or pipe it into a shell
- CC13: enableAllProjectMcpServers turned on
- CC14: file access to the whole disk, the home folder, ~/.ssh or .env files
- CC15: .env files that no Read deny rule covers
- CC16: WebFetch allowed for every domain
- CC17: sandbox escapes (Docker socket, all Unix sockets, weaker nested sandbox, broad excludedCommands or allowWrite)
- CC18: deny rules Claude Code never matches (Write(./.env), /etc/... with one slash)
What's included
- The scanner (Python 3.9+, standard library only)
- A rules guide with the reason and safer approach for each rule
- A risky and a safe example project, and the real report the scanner produces on the risky one
Limits It reads each settings file as written: settings it is not pointed at (user, managed, server-managed or --settings), hook scripts named by path, plugin hooks, .mcp.json servers and CLAUDE.md are not combined or read. NOT FLAGGED is not a guarantee.
Static check of settings file text. Settings from other scopes are not merged, and hook scripts named by path are not read. NOT FLAGGED is not a guarantee.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 days ago
Requires
Permissions
Allowed Hosts
Runs one local Python script in the terminal. It reads your project's files, writes nothing, and makes no network calls. The example project includes a clearly fake, inert API key (not-a-real-...) and sample hooks for the scanner to find. Nothing in it is run.