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/shafthq/shaft_engine/user-prompt-submitgit clone --depth 1 https://github.com/ShaftHQ/SHAFT_ENGINEWrote 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/shafthq/shaft_engine/user-prompt-submit)<a href="https://agentmods.dev/hooks/shafthq/shaft_engine/user-prompt-submit"><img src="https://agentmods.dev/badge/hooks/shafthq/shaft_engine/user-prompt-submit.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
UserPromptSubmit 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 today.
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
98% identical to PreCompact — 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.
How it starts
The opening of the file, as written. The whole thing — 14 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"UserPromptSubmit": [
{
"hooks": [
{
"command": "python3 -c \"exec(\\\"import errno,json,os,pathlib,runpy,sys\\\\nos.environ['CHAOS_ENGINE_HOST']='claude'\\\\nCWD='repository working directory unavailable; restore the original mount or checkout, then retry'\\\\nGUARD='ChaosEngine guard unavailable; repair the original installation, then retry'\\\\nE={errno.ENOENT,getattr(errno,'ESTALE',116),getattr(errno,'ENOTCONN',107)}\\\\ndef deny(message):\\\\n print(json.dumps({'decision':'block','reason':message}))\\\\n raise SystemExit(2)\\\\ntry:\\\\n cwd=pathlib.Path.cwd()\\\\n roots=(cwd,*cwd.parents)\\\\nexcept OSError as error:\\\\n deny(CWD) if error.errno in E else (_ for _ in ()).throw(error)\\\\ncands=('.chaos-engine/hooks/guard.py','plugins/chaos-engine/hooks/guard.py','chaos-engine/hooks/guard.py')\\\\ntry:\\\\n path=next((root/rel for root in roots for rel in cands if (root/rel).is_file()),None)\\\\nexcept OSError as error:\\\\n deny(CWD) if error.errno in E else (_ for _ in ()).throw(error)\\\\nif path is None:\\\\n deny(GUARD)\\\\ntry:\\\\n runpy.run_path(str(path),run_name='__main__')\\\\nexcept OSError as error:\\\\n deny(CWD) if error.errno in E else (_ for _ in ()).throw(error)\\\\n\\\")\"",
"commandWindows": "py -3 -c \"exec(\\\"import errno,json,os,pathlib,runpy,sys\\\\nos.environ['CHAOS_ENGINE_HOST']='claude'\\\\nCWD='repository working directory unavailable; restore the original mount or checkout, then retry'\\\\nGUARD='ChaosEngine guard unavailable; repair the original installation, then retry'\\\\nE={errno.ENOENT,getattr(errno,'ESTALE',116),getattr(errno,'ENOTCONN',107)}\\\\ndef deny(message):\\\\n print(json.dumps({'decision':'block','reason':message}))\\\\n raise SystemExit(2)\\\\ntry:\\\\n cwd=pathlib.Path.cwd()\\\\n roots=(cwd,*cwd.parents)\\\\nexcept OSError as error:\\\\n deny(CWD) if error.errno in E else (_ for _ in ()).throw(error)\\\\ncands=('.chaos-engine/What else settings.json configures
This page is one entry in a file that holds 10. 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.
- today Changed 66d022fd9416
- 4d ago First seen · 14 lines scan A 72998fdf7b6c
UserPromptSubmit is a hook published in the GitHub repository ShaftHQ/SHAFT_ENGINE (407 stars, last pushed yesterday), 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 98% identical to PreCompact, differing in 2 lines, and is treated as a copy.
Other hooks, from other repositories
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing format_and_lint.sh. From supabase/supabase.
SessionStart
Runs when a session starts, executing on-start.js via node. From google-gemini/gemini-cli.
SessionStart
Runs when a session starts on startup, executing install_pkgs.sh. From supabase/supabase.
PreToolUse
Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From apache/superset.
PreToolUse
Runs before the agent uses a tool, executing pre-write.sh and pre-bash.sh (2 commands). From anthropics/claude-cookbooks.
SessionStart
Runs when a session starts, executing session-start.sh. From anthropics/claude-cookbooks.