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/ij5a/subrosa/pre-compactgit clone --depth 1 https://github.com/ij5a/subrosaGrade 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 2d 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
86% identical to SessionEnd — 4 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": [
{
"hooks": [
{
"type": "command",
"command": "\"${CLAUDE_PLUGIN_ROOT}\"/hooks/run.sh pre-compact"
}
]
}
]
}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.
- 2d ago First seen · 12 lines scan A 1afc70b74d48
PreCompact is a hook published in the GitHub repository ij5a/subrosa (7 stars, last pushed 2d 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. It is 86% identical to SessionEnd, differing in 4 lines, and is treated as a copy.
Other hooks, from other repositories
PostToolUse
Runs after a tool call finishes for Edit and Write tool calls, executing cli.js. From tw93/Pake.
PreToolUse
Runs before the agent uses a tool for Edit, Write, NotebookEdit, Read, Skill, Agent and Task tool calls, executing hook-launcher.mjs and pre-agent-inject.sh via node (3 commands). From sdsrss/claude-mem-lite.
Stop
Runs when the agent finishes a response, executing session-stop.sh via bash. From FlorianBruniaux/ccboard.
PreCompact
Runs before the context is compacted, running bd prime. From dirge-code/dirge.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing pane-title.sh and workspace-status.sh via bash (2 commands). From virgil-king/kbtz.
PostToolUse
Runs after a tool call finishes for edit_file and edit_files tool calls, executing graphmind-post-tool-use.mjs via node. From kostya-pakhomov/graphmind.