Borrowing it
Nothing to install: this file belongs to melodic-software/claude-code-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/melodic-software/claude-code-plugins/main/.claude/settings.jsongit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/settings/melodic-software/claude-code-plugins/settings)<a href="https://agentmods.dev/settings/melodic-software/claude-code-plugins/settings"><img src="https://agentmods.dev/badge/settings/melodic-software/claude-code-plugins/settings/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/settings/melodic-software/claude-code-plugins/settings"><img src="https://agentmods.dev/badge/settings/melodic-software/claude-code-plugins/settings.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade B, and why
claude-code-plugins scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
"Read(./.claude/settings.local.json)", How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"$schema": "https://json.schemastore.org/claude-code-settings.json",
"autoMemoryEnabled": false,
"permissions": {
"allow": [
"mcp__claude-code-remote__add_repo",
"mcp__claude-code-remote__get_event",
"mcp__claude-code-remote__get_session",
"mcp__claude-code-remote__get_trigger",
"mcp__claude-code-remote__list_environments",
"mcp__claude-code-remote__list_events",
"mcp__claude-code-remote__list_repos",
"mcp__claude-code-remote__list_sessions",
"mcp__claude-code-remote__list_triggers",
"mcp__claude-code-remote__read_documentation",
"mcp__claude-code-remote__register_repo_root",
"mcp__claude-code-remote__set_session_tags",
"mcp__claude-code-remote__set_session_title",
"mcp__claude-code-remote__subscribe_pr_activity",
"mcp__claude-code-remote__unsubscribe_pr_activity"
],
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(./secrets/**)",
"Read(./.claude/settings.local.json)",
"Read(**/*.key)",
"Read(**/*.pem)",
"Read(**/id_rsa)"
]
},
"env": {
"CLAUDE_CODE_DISABLE_AUTO_MEMORY": "1",
"HOOK_TELEMETRY_SINK": ".claude/hooks/hook-telemetry-sink.sh"
},
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"if": "Bash(git push *)",
"command": "if git -C \"$CLAUDE_PROJECT_DIR\" diff --quiet \"$(git -C \"$CLAUDE_PROJECT_DIR\" merge-base HEAD refs/remotes/origin/main 2>/dev/null)\" -- .claude/hooks/check-affected-pre-push.sh lib/hook-utils.sh 2>/dev/null; then bash \"$CLAUDE_PROJECT_DIR/.claude/hooks/check-affected-pre-push.sh\"; fi"
}
]
}
],
"SessionStart": [
{
"matcher": "startup|resume",
"hooks": [
{
"type": "command",
"command": "bash \"$CLAUDE_PROJECT_DIR/.claude/cloud-bootstrap.sh\""
}
]
}
]
},
What else settings.json configures
This page is one entry in a file that holds 3. Installing the file brings all of them; each is measured and scanned on its own page.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · -8 lines e1fb575e7fa0
- 4d ago Changed · +13 lines dfb7b72573f7
- 5d ago Changed 6ebcadd7fcef
- 9d ago Changed · +18 lines d109c4c91437
- 12d ago Changed · +4 lines c9cf4ada55c7
- 13d ago Changed · +3 lines 0f9460a9e2ed
- 14d ago Changed · +1 lines b7162a4eaaa4
- 16d ago Changed · +1 lines 7b626049cff3
- 17d ago Changed · +1 lines 62ebed2107e5
- 18d ago First seen · 50 lines scan B de3c4e597be0
claude-code-plugins is a settings file published in the GitHub repository melodic-software/claude-code-plugins (25 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other settings, from other repositories
supabase
Agent settings declaring 2 hook events (SessionStart, PostToolUse).
superset
Agent settings declaring 1 hook event (PreToolUse).
claude-cookbooks
Agent settings declaring 2 hook events (SessionStart, PreToolUse).
RuView
Agent settings declaring 8 hook events (PreToolUse, PostToolUse, UserPromptSubmit, SessionStart) and 4 allowed tools.
orm
Agent settings declaring 4 hook events (PreToolUse, PostToolUse, WorktreeCreate, Stop) and 21 allowed tools.
claude-code-best-practice
Agent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools.