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/hehee9/codex-compressor/pre-compactgit clone --depth 1 https://github.com/hehee9/codex-compressorGrade 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- PostCompact — 92% identical, 4 lines differ
- SessionStart — 86% identical, 6 lines differ
What it actually says
{
"PreCompact": [
{
"matcher": "^(auto|manual)$",
"hooks": [
{
"type": "command",
"command": "python3 \"${PLUGIN_ROOT}/hooks/launch.py\"",
"commandWindows": "py -3 \"${PLUGIN_ROOT}\\hooks\\launch.py\"",
"timeout": 10,
"statusMessage": "롤오버 체크포인트 저장"
}
]
}
]
}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 · 16 lines scan A 9b55e093dbb6
PreCompact is a hook published in the GitHub repository hehee9/codex-compressor (10 stars, last pushed 7d 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other hooks, from other repositories
PreToolUse
Runs before the agent uses a tool for local_shell, shell, shell_command, exec_command, terminal, Bash, Shell, sh, zsh, fish, powershell, pwsh, cmd, write_stdin, grep_files, mcp__, spawn_agent, collaboration, read_thread and codex_app tool calls, executing hook.cjs via node with --no-warnings. From hakiyaka/capsule.
PostToolUse
Runs after a tool call finishes, executing hook.cjs via node with --no-warnings. From hakiyaka/capsule.
SessionStart
Runs when a session starts, executing hook.cjs via node with --no-warnings. From hakiyaka/capsule.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing hook.cjs via node with --no-warnings. From hakiyaka/capsule.
Stop
Runs when the agent finishes a response, executing hook.cjs via node with --no-warnings. From hakiyaka/capsule.
SessionStart
Runs when a session starts on startup, resume, clear and compact, executing hook.mjs via node. From Kolikkii/token-razor.