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/muratsilahtaroglu/claude-code-starter-kit/pre-compactgit clone --depth 1 https://github.com/muratsilahtaroglu/claude-code-starter-kitGrade 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
44% identical to SessionStart — 20 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": "${CLAUDE_PROJECT_DIR}/.claude/hooks/pre-compact-snapshot.sh"
},
{
"type": "command",
"command": "${CLAUDE_PROJECT_DIR}/.claude/hooks/ritual-log.sh"
}
]
},
{
"matcher": "manual",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PROJECT_DIR}/.claude/hooks/compact-gate.sh"
}
]
}
]
}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 · 25 lines scan A 1f4a5193584c
PreCompact is a hook published in the GitHub repository muratsilahtaroglu/claude-code-starter-kit (9 stars, last pushed 5d 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 44% identical to SessionStart, differing in 20 lines, and is treated as a copy.
Other hooks, from other repositories
SessionStart
Runs when a session starts on startup and resume, executing hlpm-ping.sh, session-start-cycle-reset.sh and session-start-hook.sh via bash (4 commands). From lwalden/AIAgentMinder.
PreToolUse
Runs before the agent uses a tool for Agent, Bash and mcp__github__create_pull_request tool calls, executing sprint-phase-guard.sh and pre-pr-gate-hook.sh via bash (3 commands). From lwalden/AIAgentMinder.
Stop
Runs when the agent finishes a response, executing sprint-stop-guard.sh, context-warning-hook.sh and sprint-phase-reminder.sh via bash (3 commands). From lwalden/AIAgentMinder.
StopFailure
Runs on the StopFailure event, executing stop-failure-hook.sh via bash. From lwalden/AIAgentMinder.
SessionStart
Runs when a session starts on startup, resume, clear and compact, running an inline shell check. From Nevaberry/nevaberry-plugins.
SessionEnd
Runs when a session ends, executing hlpm-ping.sh via bash. From lwalden/AIAgentMinder.