skills-benchmarks is a test suite that measures how the design of skill documentation affects Claude Code's adherence to recommended coding patterns. It is used to compare documentation approaches across LangChain-related tasks and other agent workflows. Its catalogue entries represent skills, hooks, instructions, and a plugin used in the benchmark project.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add langchain-ai/skills-benchmarks/plugin install langsmith-tracingWrote 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/langchain-ai/skills-benchmarks/user-prompt-submit)<a href="https://agentmods.dev/hooks/langchain-ai/skills-benchmarks/user-prompt-submit"><img src="https://agentmods.dev/badge/hooks/langchain-ai/skills-benchmarks/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/langchain-ai/skills-benchmarks/user-prompt-submit"><img src="https://agentmods.dev/badge/hooks/langchain-ai/skills-benchmarks/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.
Copies of this mod
1 near-identical copy found in the catalogue:
- UserPromptSubmit — 100% identical, 0 lines differ
What it actually says
{
"UserPromptSubmit": [
{
"hooks": [
{
"type": "command",
"command": "node \"${CLAUDE_PLUGIN_ROOT}/bundle/user-prompt-submit.js\"",
"timeout": 30
}
]
}
]
}What else hooks.json configures
This page is one entry in a file that holds 9. 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.
- 9d ago First seen · 13 lines scan A 075c6936a642
UserPromptSubmit is a hook published in the GitHub repository langchain-ai/skills-benchmarks (116 stars, last pushed 21d 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 2026-08-30.
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 on startup, executing install_pkgs.sh. From supabase/supabase.
SessionStart
Runs when a session starts, executing on-start.js via node. From google-gemini/gemini-cli.
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.
PreCompact
Runs before the context is compacted for manual and auto tool calls, executing hook-handler.cjs via node (4 commands). From ruvnet/RuView.