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/dz1922/claude-notify/stopgit clone --depth 1 https://github.com/dz1922/claude-notifyGrade A, and why
Stop 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.
What it actually says
{
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "CLAUDE_HOOK_EVENT=Stop ${CLAUDE_PLUGIN_ROOT}/hooks/notify.sh",
"timeout": 10
}
]
}
]
}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 · 13 lines scan A a55a8a8734a7
Stop is a hook published in the GitHub repository dz1922/claude-notify (1 stars, last pushed 5mo ago), 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other hooks, from other repositories
PreToolUse
Runs before the agent uses a tool for Skill, Bash, Write, Edit, MultiEdit and NotebookEdit tool calls, executing guard.sh (3 commands). From wookiya1364/scv-claude-code.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing on-user-prompt.sh. From wookiya1364/scv-claude-code.
Stop
Runs when the agent finishes a response, executing on-stop.sh. From wookiya1364/scv-claude-code.
SubagentStop
Runs when a subagent finishes, running sh. From 777genius/claude-notifications-go.
PermissionRequest
Runs when the agent asks permission for an action, executing hook.sh via bash. From Affirm/navi.
Stop
Runs when the agent finishes a response, running powershell. From Fergal7/cc-sounds.