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/sahithvibudhi/vibe-tree/notificationgit clone --depth 1 https://github.com/sahithvibudhi/vibe-treeWrote 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/hooks/sahithvibudhi/vibe-tree/notification)<a href="https://agentmods.dev/hooks/sahithvibudhi/vibe-tree/notification"><img src="https://agentmods.dev/badge/hooks/sahithvibudhi/vibe-tree/notification.svg" alt="Measured on agentmods" height="20"></a>Grade B, and why
Notification 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 5d ago.
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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
"command": "curl -X POST http://127.0.0.1:7878/notification -H \"Content-Type: application/json\" -d '{\"type\": \"claude-needs-input\", \"worktree\": \"'$PWD'\", \"message\": \"'$CLAUDE_NOTIFICATION'\"}' --silent --fail Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"command": "curl -X POST http://127.0.0.1:7878/notification -H \"Content-Type: application/json\" -d '{\"type\": \"claude-needs-input\", \"worktree\": \"'$PWD'\", \"message\": \"'$CLAUDE_NOTIFICATION'\"}' --silent --fail What it actually says
{
"Notification": [
{
"hooks": [
{
"type": "command",
"command": "curl -X POST http://127.0.0.1:7878/notification -H \"Content-Type: application/json\" -d '{\"type\": \"claude-needs-input\", \"worktree\": \"'$PWD'\", \"message\": \"'$CLAUDE_NOTIFICATION'\"}' --silent --fail || true"
}
]
}
]
}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.
- 5d ago First seen · 12 lines scan B 0363bbfca346
Notification is a hook published in the GitHub repository sahithvibudhi/vibe-tree (267 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other hooks, from other repositories
PostToolUse
Runs after a tool call finishes for Edit and Write tool calls, running an inline shell check. From KhazP/vibe-coding-prompt-template.
PreToolUse
Runs before the agent uses a tool for Edit, Write, Grep, Glob, Bash, Edit, Write, NotebookEdit and Bash tool calls, executing spec-hint.js, module-hint.js and docs-hint.js via node (3 commands). From kaanozhan/Frame.
SessionStart
Runs when a session starts on compact, running an inline shell check. From matt1398/claude-devtools.
PostToolUse
Runs after a tool call finishes for Edit, Write and NotebookEdit tool calls, running an inline shell check. From matt1398/claude-devtools.
PreToolUse
Runs before the agent uses a tool for Edit, Write and MultiEdit tool calls, running an inline shell check. From kevinlin/cowork-z.
PostToolUse
Runs after a tool call finishes, running vibird hook PostToolUse. From Hakureirm/vibird.