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/hedde/trigger_tree/user-prompt-submitgit clone --depth 1 https://github.com/Hedde/trigger_treeGrade 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 yesterday.
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 SessionStart — 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
{
"UserPromptSubmit": [
{
"hooks": [
{
"type": "command",
"command": "H=\"${CLAUDE_PLUGIN_ROOT}/scripts/tt-codex-hook.py\"; [ -f \"$H\" ] || exit 0; if command -v python3 >/dev/null 2>&1; then exec python3 \"$H\" --client codex; else exec python \"$H\" --client codex; fi",
"commandWindows": "if exist \"%CLAUDE_PLUGIN_ROOT%\\scripts\\tt-codex-hook.py\" py -3 \"%CLAUDE_PLUGIN_ROOT%\\scripts\\tt-codex-hook.py\" --client codex",
"timeout": 5
}
]
}
]
}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.
- yesterday First seen · 14 lines scan A c19aa737d166
UserPromptSubmit is a hook published in the GitHub repository Hedde/trigger_tree (14 stars, last pushed 8d 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 98% identical to SessionStart, differing in 2 lines, and is treated as a copy.
Other hooks, from other repositories
PostToolUse
Runs after a tool call finishes for ^mcp__plugin_datadog_mcp__(get_widget and visualize_tabular_data)$ tool calls, running bash. From datadog-labs/claude-code-plugin.
SessionEnd
Runs when a session ends, running bash. From datadog-labs/claude-code-plugin.
PostToolUse
Runs after a tool call finishes for Edit and Write tool calls, executing sourcebook-validate.sh via bash. From BackendGameSetMatch/sourcebook.
SessionStart
Runs when a session starts, executing session-start.js via node. From raccioly/docguard.
SessionStart
Runs when a session starts on startup, running an inline shell check. From nicholasglazer/gnosis-mcp.
PreToolUse
Runs before the agent uses a tool for Bash, Bash, Write, Edit and MultiEdit tool calls, executing dispatch.py and before_write.py via python3 (2 commands). From WangChangxin0809/repo-agent-harness.