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 hooks/punt-labs/vox/notificationgit clone --depth 1 https://github.com/punt-labs/voxGrade A, and why
Notification scanned grade A with 0 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 yesterday.
A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
66% identical to SessionStart — 19 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"Notification": [
{
"matcher": "permission_prompt",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/notify-permission.sh",
"async": true
}
]
},
{
"matcher": "idle_prompt",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/notify-permission.sh",
"async": true
}
]
}
]
}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 First seen · 24 lines scan A 47cbfbf128f0
Notification is a hook published in the GitHub repository punt-labs/vox (3 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it A with 0 findings. It is 66% identical to SessionStart, differing in 19 lines, and is treated as a copy.
Other hooks, from other repositories
PostToolUse
Runs after a tool call finishes for Task and TodoWrite tool calls, running entire hooks claude-code post-task (2 commands). From punt-labs/langlearn-tts.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, running entire hooks claude-code user-prompt-submit. From punt-labs/langlearn-tts.
SessionStart
Runs when a session starts, running entire hooks claude-code session-start. From punt-labs/langlearn-tts.
SessionEnd
Runs when a session ends, running entire hooks claude-code session-end. From punt-labs/langlearn-tts.
Stop
Runs when the agent finishes a response, running entire hooks claude-code stop. From punt-labs/langlearn-tts.
PreToolUse
Runs before the agent uses a tool for Task tool calls, running entire hooks claude-code pre-task. From punt-labs/langlearn-tts.