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.
git clone --depth 1 https://github.com/swapii/claude-linguistWrote 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/swapii/claude-linguist/user-prompt-submit)<a href="https://agentmods.dev/hooks/swapii/claude-linguist/user-prompt-submit"><img src="https://agentmods.dev/badge/hooks/swapii/claude-linguist/user-prompt-submit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/hooks/swapii/claude-linguist/user-prompt-submit"><img src="https://agentmods.dev/badge/hooks/swapii/claude-linguist/user-prompt-submit.svg" alt="Reviewed on agentmods" width="80" 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 9d 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.
What it actually says
{
"UserPromptSubmit": [
{
"hooks": [
{
"type": "command",
"command": "echo '{\"hookSpecificOutput\":{\"hookEventName\":\"UserPromptSubmit\",\"additionalContext\":\"Use the review-user-prompt-english skill to check the user message for English mistakes. Invoke the Skill tool with skill: review-user-prompt-english.\"}}'",
"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.
- 9d ago First seen · 13 lines scan A d23d298da61d
UserPromptSubmit is a hook published in the GitHub repository swapii/claude-linguist (3 stars, last pushed 4mo 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other hooks, from other repositories
PostCompact
Runs after the context is compacted, executing post-compact.sh via bash. From IdoCohen560/claude-unity-game-studio.
Notification
Runs when the agent sends a notification, executing notify.sh via bash. From IdoCohen560/claude-unity-game-studio.
Stop
Runs when the agent finishes a response, executing session-stop.sh via bash. From IdoCohen560/claude-unity-game-studio.
PostToolUse
Runs after a tool call finishes for ^mcp__plugin_qector_qector-(library, research and admin)__.*$ tool calls, executing qector_tool_log.py. From GuillaumeLessard/qector-claude-plugin.
SessionStart
Runs when a session starts, executing session-start.sh and detect-gaps.sh via bash (2 commands). From IdoCohen560/claude-unity-game-studio.
PreToolUse
Runs before the agent uses a tool for Bash tool calls, executing validate-commit.sh and validate-push.sh via bash (2 commands). From IdoCohen560/claude-unity-game-studio.