# Agent Reliability Skills

MCP server Agent Reliability Skills for Claude Code generates a pre-coding SKILL.md file based on repository dependencies.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 62 repo stars
- Author: trustabl
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/trustabl/agent-reliability-skills
- Updated: 2026-11-15
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/agent-reliability-skills

## What it does

The server checks dependency manifests like `package.json` or `pyproject.toml`, detects agent SDKs, and builds a rules skill from Trustabl detection logic. An agent reads this skill to follow standards while writing code. The tool downloads the appropriate analyzer binary, verifies it against `checksums.txt`, and caches it locally.

Node.js version 22 or later is required. The initial call fetches the analyzer binary and rules repository, allowing subsequent runs to operate completely offline from cache without requiring a `git` binary.

## Requirements
- Needs: Node.js (commands run via npx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add agent-reliability-skills -- npx -y @trustabl/agent-reliability-skills
```

### Codex

**Platform CLI**
```bash
codex mcp add agent-reliability-skills -- npx -y @trustabl/agent-reliability-skills
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "agent-reliability-skills": {
            "command": "npx",
            "args": [
                "-y",
                "@trustabl/agent-reliability-skills"
            ]
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "agent-reliability-skills": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@trustabl/agent-reliability-skills"
            ]
        }
    }
}
```

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add agent-reliability-skills npx -y @trustabl/agent-reliability-skills
```

## When to use it
- generate a custom `SKILL.md` file from project manifests
- apply reliability rules for OpenAI Agents SDK and Claude Agent SDK
- verify analyzer release checksums on first execution
- build detection rules for LangChain, LangGraph and CrewAI

## Example prompts
- Generate the Trustabl pre-coding skill for my repository and write it to `.claude/skills/trustabl-pre-coding/SKILL.md`
- Run the `trustabl_forge` tool with the path of the workspace
- Add the `openai_sdk` policy category via MCP tool input

## Similar
- [reliability-strategy-builder](https://affpapa.org/en/nevibecode/skills/reliability-strategy-builder.md) — skill · 273 installs
- [steel-reliability](https://affpapa.org/en/nevibecode/skills/steel-reliability.md) — skill · 483 installs
- [azure-reliability](https://affpapa.org/en/nevibecode/skills/microsoftdocs-azure-reliability.md) — skill · 186 installs
- [google-cloud-waf-reliability](https://affpapa.org/en/nevibecode/skills/google-cloud-waf-reliability.md) — skill · 14039 installs
- [gke-reliability](https://affpapa.org/en/nevibecode/skills/gke-reliability.md) — skill · 6500 installs
- [cortx-reliability](https://affpapa.org/en/nevibecode/skills/cortx-reliability.md) — skill · ★ 797 repo stars

From the same set: [trustabl/agent-reliability-skills](https://affpapa.org/en/nevibecode/by/trustabl/agent-reliability-skills.md) — 4 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
