Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add settings/oikon48/claudecode-book/settingsgit clone --depth 1 https://github.com/oikon48/claudecode-bookGrade B, and why
claudecode-book scanned grade B with 2 findings 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 2d ago.
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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
"Bash(sudo *)", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"Bash(curl:*)", What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-settings.json",
"permissions": {
"defaultMode": "plan",
"allow": [
"Bash(npm run lint)",
"Bash(npm run test:run)",
"Bash(npm run build)"
],
"ask": [
"Bash(npm install *)",
"Bash(git push *)",
"Bash(rm *)"
],
"deny": [
"Read(.env*)",
"Bash(curl:*)",
"Bash(sudo *)",
"Bash(git push --force *)",
"WebFetch(domain:attacker.example.com)"
]
},
"hooks": {
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "osascript -e 'display notification \"Claude Codeがタスクを終了しました\" with title \"Claude Code\"'"
}
]
}
],
"PostToolUse": [
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR/.claude/hooks/check-after-edit.sh\""
}
]
}
],
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR/.claude/hooks/block-dangerous-command.sh\""
}
]
}
]
},
"sandbox": {
"enabled": true,
"autoAllowBashIfSandboxed": true,
"allowUnsandboxedCommands": true,
"filesystem": {
"denyRead": [
".env",
".env.*",
"**/.env",
"**/.env.*"
]
},
"network": {
"allowedDomains": [
"github.com",
"registry.npmjs.org"
]
}
},
"env": {
"CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS": "1"
}
}
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.
- 2d ago First seen · 80 lines scan B 4c595be21c2c
claudecode-book is a settings file published in the GitHub repository oikon48/claudecode-book (5 stars, last pushed 20d ago), 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 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other settings, from other repositories
cli
AI Instructions Diagnostics | Supported agents: Claude | Codex | Copilot | Cursor | Gemini.
claude-agents-md
Agent settings configuring hooks.
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).
claude-code-best-practice
Agent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools.