Agent Reliability Skills runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 6 Nov 2026.
Generates a pre-coding reliability skill (SKILL.md) for your agent repo from Trustabl's rules.
Today is the operative word: we check Agent Reliability Skills every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add agent-reliability-skills -- npx -y @trustabl/agent-reliability-skills
{
"mcpServers": {
"agent-reliability-skills": {
"command": "npx",
"args": [
"-y",
"@trustabl/agent-reliability-skills"
]
}
}
}
[mcp_servers.agent-reliability-skills]
command = "npx"
args = ["-y", "@trustabl/agent-reliability-skills"]
{
"mcpServers": {
"agent-reliability-skills": {
"command": "npx",
"args": [
"-y",
"@trustabl/agent-reliability-skills"
]
}
}
}
{
"servers": {
"agent-reliability-skills": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@trustabl/agent-reliability-skills"
]
}
}
}
Scan a GitHub repository for vulnerabilities, with proof for every finding, from your coding agent.
Generate and validate a .specs/ bundle for your repo, then hand it to your AI coding agent
Find and fix reliability and safety gaps in agent code, across nine agent SDKs.
Your repository's engineering standards for coding agents: rules per file, CI check, rule proposals.
Trust score for AI-generated code: scan repos, guard agent file writes, get a 0-100 score.
Analyzes codebases with tree-sitter and generates AGENTS.md files for AI coding agents.
Watch your coding agent work as a film: opens and replays the Agent Theatre stage for a repo.
A/B testing for vibe coders: create, track, and ship experiments from your AI coding agent.
Answers built from our own checks of this server.