Schliff

Schliff is an open-source linting, scoring, and verification harness developed by Zandereins designed for AI agent configuration ecosystems. It targets repository-level agent instruction files (such as AGENTS.md), agent skill meshes, and plugin specifications to ensure multi-agent instructions remain valid, non-colliding, and structurally sound. In day-to-day workflows, Schliff runs via a terminal CLI, pre-commit hooks, or CI/CD pipelines (such as GitHub Actions). Developers use it to inspect agent instruction health, check for overlapping skill definitions, and diagnose registry errors using subcommands like `schliff score AGENTS.md`, `schliff doctor`, and `schliff mesh`. For semantic evaluations, it also offers an optional LLM judge component backed by the Anthropic SDK. Schliff differentiates itself from runtime execution harnesses by acting as a dedicated static analysis and validation engine specifically tuned for agent architecture specs. Rather than executing prompts against a codebase, it validates the structural integrity and mesh definitions of agent toolsets and instructions before agents are run or merged. Schliff is open source and available as a Python package via PyPI, a pre-commit hook, and a GitHub Marketplace Action.

Tags: ai agent, cli, coding agent, developer tools, OpenSource, prompts

Visit Schliff

Key features

• AGENTS.md Scoring — Analyzes and calculates health scores for instruction files and agent configurations directly from the terminal. - Mesh & Collision Detection — Scans agent skill registries to identify duplicate names, schema collisions, and conflicting tooling definitions. - Diagnostics Tools — Provides dedicated doctor and mesh CLI subcommands to verify local environments and agent mesh integrity. - CI/CD & GitHub Action Support — Integrates into automation workflows via the official agents-md-lint-schliff GitHub Action and pre-commit hooks. - Claude Plugin Integration — Provides structural support and validation routines for .claude-plugin definitions. - Optional LLM Judge Evaluation — Supports an optional [judge] dependency extra using Anthropic models to perform deeper qualitative checks.

Use cases

Use Case: Enforcing Agent Configuration Standards in CI Platform teams integrate agents-md-lint-schliff into GitHub Actions workflows to prevent pull requests from introducing broken, duplicate, or unformatted AGENTS.md instructions into production repositories.

Use Case: Auditing Multi-Agent Tool and Skill Meshes Developers building complex multi-agent skill suites run schliff mesh and schliff doctor locally to detect duplicate skill declarations and collision defects before deployment.

Use Case: Pre-Commit Quality Checks for AI Instructions Engineers set up Schliff as a pre-commit hook to lint agent markdown configurations and plugin manifests on every local commit, catching regression defects before pushing changes.

Who it is for

Schliff is built for AI engineers, DevOps teams, and platform developers maintaining repository-level agent instruction files (AGENTS.md), custom Claude plugins, and multi-skill agent meshes. It is not an interactive terminal coding assistant itself, but a specialized validation harness and linter for teams orchestrating agent architectures.

Install guide

Installation Install Schliff from PyPI using pip or pipx: bash pip install schliff # Or install with optional Anthropic judge capabilities pip install "schliff[judge]" Alternatively, add it to your .pre-commit-config.yaml: yaml repos: - repo: https://github.com/Zandereins/schliff rev: 8.11.1 hooks: - id: schliff

First Run No authentication is required for static linting, mesh inspection, or score calculations. If using the optional judge functionality, set your Anthropic API key: bash export ANTHROPIC_API_KEY="your-anthropic-api-key"

Example Session Run diagnostic checks and score an AGENTS.md file: bash # Verify environment and skill mesh health schliff doctor # Lint and score your agent instruction file schliff score AGENTS.md

Part of CLI Coding Agents

Categories: AI Coding Agents, Developer Tools, Prompts

Related CLI agents

• OpenCode — OpenCode is an open-source AI coding agent developed by Anomaly that operates across terminal environments, desktop applications, and IDE extensions.…
• goose — goose is an open-source, general-purpose AI agent built in Rust, hosted under the vendor-neutral Agentic AI Foundation (AAIF) at the…
• SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
• OpenHands — OpenHands (formerly OpenDevin) is an open-source autonomous AI software development agent and orchestration platform. It provides an extensible runtime environment…
• Plandex — Plandex is an open-source terminal-based AI coding agent designed to handle complex, multi-file engineering tasks in large codebases. Created by…
• Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…