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/sting25/claude-code-handoff/pre-compactgit clone --depth 1 https://github.com/Sting25/claude-code-handoffGrade 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
91% identical to SessionEnd — 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": "bash \"${CLAUDE_PLUGIN_ROOT}/bin/write_handoff.sh\" --if-curated >/dev/null 2>&1 || true",
"timeout": 60
}
]
}
]
}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 · 13 lines scan A ec55dc7732a9
PreCompact is a hook published in the GitHub repository Sting25/claude-code-handoff (4 stars, last pushed 3d 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 91% identical to SessionEnd, differing in 2 lines, and is treated as a copy.
Other hooks, from other repositories
Stop
Runs when the agent finishes a response, running context-mode hook antigravity-cli stop. From mksglu/context-mode.
PreToolUse
Runs before the agent uses a tool for Skill, Agent and Task tool calls, executing pre_skill_execution.py and agent_dispatch_guard.py (2 commands). From athola/claude-night-market.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing aggregate_learnings_daily.py. From athola/claude-night-market.
PreToolUse
Runs before the agent uses a tool for Read, Edit, Write, Read, Grep, Task and Edit tool calls, executing pre-tool-use-broadcast.mjs, path-rules.mjs, tldr-read-enforcer.mjs, smart-search-router.mjs, tldr-context-inject.mjs, arch-context-inject.mjs, file-claims.mjs, edit-context-inject.mjs and signature-helper.mjs via…
Stop
Runs when the agent finishes a response, executing hook_launcher.py, stop_hook.sh and compiler-in-the-loop-stop.mjs via uv (3 commands). From parcadei/Continuous-Claude-v3.
PreToolUse
Runs before the agent uses a tool for Artifact tool calls, running python. From WatsonTsai/smart-brief.