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/reikor-arg/inmemory/pre-compactgit clone --depth 1 https://github.com/Reikor-Arg/inmemoryGrade 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 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.
This is a copy
94% identical to Stop — 2 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": "sh \"${CLAUDE_PLUGIN_ROOT}/hooks/run.sh\" recall.mjs hook-index",
"commandWindows": "if (Get-Command node -ErrorAction SilentlyContinue) { node \"$env:CLAUDE_PLUGIN_ROOT\\hooks\\recall.mjs\" hook-index }",
"timeout": 30
}
]
}
]
}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 · 14 lines scan A 1babec716b64
PreCompact is a hook published in the GitHub repository Reikor-Arg/inmemory (1 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. It is 94% identical to Stop, differing in 2 lines, and is treated as a copy.
Other hooks, from other repositories
SessionStart
Runs when a session starts on startup, resume, clear, compact and compact, executing session-start.sh and compact-restore.sh via bash (2 commands). From joseairosa/recall.
SessionEnd
Runs when a session ends, executing tracker.js. From egorfedorov/claude-context-optimizer.
SessionEnd
Runs when a session ends, executing cleanup_session_cache.py via python3. From Rylaa/fable5-opus5-orchestrator.
PreToolUse
Runs before the agent uses a tool for Bash, Write, Edit, Bash, Task, Task and Agent tool calls, executing run-py.sh and context-warning.sh via bash (4 commands). From primeline-ai/evolving-lite.
PostToolUse
Runs after a tool call finishes for Write, Edit and MultiEdit tool calls, running node. From paceaitian/paceflow.
PreCompact
Runs before the context is compacted, running kin compact-hook --emit-context. From jmcentire/kindex.