Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add softspark/ai-toolkit/plugin install ai-toolkitWrote 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/softspark/ai-toolkit/pre-compact)<a href="https://agentmods.dev/hooks/softspark/ai-toolkit/pre-compact"><img src="https://agentmods.dev/badge/hooks/softspark/ai-toolkit/pre-compact/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/hooks/softspark/ai-toolkit/pre-compact"><img src="https://agentmods.dev/badge/hooks/softspark/ai-toolkit/pre-compact.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
PreCompact 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 1mo 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.
This is a copy
81% identical to UserPromptSubmit — 6 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
{
"PreCompact": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "AI_TOOLKIT_DIR=\"${CLAUDE_PLUGIN_ROOT}\" \"${CLAUDE_PLUGIN_ROOT}/hooks/pre-compact.sh\""
}
]
},
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "AI_TOOLKIT_DIR=\"${CLAUDE_PLUGIN_ROOT}\" \"${CLAUDE_PLUGIN_ROOT}/hooks/pre-compact-save.sh\""
}
]
}
]
}What else hooks.json configures
This page is one entry in a file that holds 14. Installing the file brings all of them; each is measured and scanned on its own page.
- Hook ConfigChange A not measured
- Hook InstructionsLoaded A not measured
- Hook Notification A not measured
- Hook PostToolUse A not measured
- Hook PreToolUse A not measured
- Hook SessionEnd A not measured
- Hook SessionStart A not measured
- Hook Stop A not measured
- Hook SubagentStart A not measured
- Hook SubagentStop A not measured
- Hook TaskCompleted A not measured
- Hook TeammateIdle A not measured
- Hook UserPromptSubmit A not measured
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.
- 1mo ago First seen · 22 lines scan A b85c307a149c
PreCompact is a hook published in the GitHub repository softspark/ai-toolkit (181 stars, last pushed 11d ago), licensed Apache-2.0. 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 81% identical to UserPromptSubmit, differing in 6 lines, and is treated as a copy.
Other hooks, from other repositories
SessionStart
Runs when a session starts on startup, executing install_pkgs.sh. From supabase/supabase.
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing format_and_lint.sh. From supabase/supabase.
SessionStart
Runs when a session starts, executing on-start.js via node. From google-gemini/gemini-cli.
PreToolUse
Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From apache/superset.
PreToolUse
Runs before the agent uses a tool, executing pre-write.sh and pre-bash.sh (2 commands). From anthropics/claude-cookbooks.
PostToolUse
Runs after a tool call finishes for Bash tool calls, executing hooks.sh via sh (3 commands). From anthropics/claude-plugins-official.