agentmods.dev

Notification

A notification hook that runs a shell script when the agent sends a notification.

In plain words
What is it for?
Use it to run caliber-freshness-notify.sh whenever a notification is sent.
Why use it?
It gives a script a chance to check or react to agent notifications, including warnings about outdated settings.

Hook for Claude Code

1.3k +4 1mo ago A scan tokens not measured original MIT
View the source file caliber-ai-org/ai-setup
Install

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.

agentmods
npx agentmods add hooks/caliber-ai-org/ai-setup/notification
Clone the repo
git clone --depth 1 https://github.com/caliber-ai-org/ai-setup

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade 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 3d 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.

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.

.claude/settings.json · 14 lines

What it actually says

{
  "Notification": [
    {
      "matcher": "",
      "hooks": [
        {
          "type": "command",
          "command": "\"$CLAUDE_PROJECT_DIR/.claude/hooks/caliber-freshness-notify.sh\"",
          "description": "Caliber: warn when agent configs are stale"
        }
      ]
    }
  ]
}
Changes

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.

  1. 3d ago First seen · 14 lines scan A 32359d5a842d

Subscribe to this mod's changes

Notification is a hook published in the GitHub repository caliber-ai-org/ai-setup (1,259 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 A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

agent-configai-agentsanthropicclaude-codeclaude-mdcli
Related

Other hooks, from other repositories

PreToolUse

Runs before the agent uses a tool for Bash and Bash tool calls, running set -e (2 commands). From solanabr/solana-ai-kit.

solanabr/solana-ai-kit · not measured

PostToolUse

Runs after a tool call finishes for Write, Edit, Bash and Bash tool calls, running an inline shell check (3 commands). From solanabr/solana-ai-kit.

solanabr/solana-ai-kit · not measured

Stop

Runs when the agent finishes a response, running an inline shell check. From solanabr/solana-ai-kit.

solanabr/solana-ai-kit · not measured

SubagentStop

Runs when a subagent finishes, running an inline shell check. From solanabr/solana-ai-kit.

solanabr/solana-ai-kit · not measured

SessionStart

Runs when a session starts on compact, executing reload-claude-md.sh. From coo-quack/do-not-compact.

coo-quack/do-not-compact · not measured

SessionStart

Runs when a session starts, executing reinject-rules.mjs via node. From syf2211/ruledoctor.

syf2211/ruledoctor · not measured