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/kolikkii/token-razor/post-compactgit clone --depth 1 https://github.com/Kolikkii/token-razorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/hooks/kolikkii/token-razor/post-compact)<a href="https://agentmods.dev/hooks/kolikkii/token-razor/post-compact"><img src="https://agentmods.dev/badge/hooks/kolikkii/token-razor/post-compact.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
PostCompact 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 4d 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 SessionStart — 7 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
{
"PostCompact": [
{
"matcher": "manual|auto",
"hooks": [
{
"type": "command",
"command": "node \"${PLUGIN_ROOT}/scripts/hook.mjs\"",
"commandWindows": "if (Get-Command node -ErrorAction SilentlyContinue) { node \"$env:PLUGIN_ROOT\\scripts\\hook.mjs\" }",
"timeout": 5
}
]
}
]
}What else hooks.json configures
This page is one entry in a file that holds 6. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 4d ago First seen · 15 lines scan A d28835151d93
PostCompact is a hook published in the GitHub repository Kolikkii/token-razor (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 86% identical to SessionStart, differing in 7 lines, and is treated as a copy.
Other hooks, from other repositories
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, running an inline shell check. From susomejias/rembric.
PreToolUse
Runs before the agent uses a tool for ^new_context$ tool calls, executing launch.py via python3. From hehee9/codex-compressor.
PreCompact
Runs before the context is compacted for ^(auto and manual)$ tool calls, executing launch.py via python3. From hehee9/codex-compressor.
PreToolUse
Runs before the agent uses a tool for Read tool calls, executing check-file-size.sh. From richardwhiteii/rlm.
PreToolUse
Runs before the agent uses a tool for Write, Edit and MultiEdit tool calls, executing trovex-md-guard.sh. From TsukumoHQ/trovex.
PreToolUse
Runs before the agent uses a tool for Write, Write, Edit, Read and EnterPlanMode tool calls, executing archcodex-pre-write.sh, archcodex-reminder.sh, archcodex-pre-read.sh and archcodex-plan-mode.sh (4 commands). From ArchCodexOrg/archcodex.