harness-eval

A linter for AI code agent setups, not for code. It auto-detects which AI tools a project uses (Claude Code, Cursor, Windsurf, Cline, Copilot, Gemini CLI, OpenCode), builds a component graph across all of them, and runs 92 deterministic rules to catch issues that per-file linters miss: credential exfiltration chains, confused deputy attacks, skill/hook conflicts, and token budget blowouts.

Most tools test whether a skill produces correct output. This one checks the setup itself: CLAUDE.md, GEMINI.md, AGENTS.md, skills, commands, hooks, MCP configs, agents, .cursor/rules/*.mdc, .cursorrules, .github/prompts/, .opencode/.

Quick start

pip install harness-eval
harness-eval harness-lint .          # 92 deterministic rules, fully offline
harness-eval harness-security .      # security scan (18 rules)

See docs/INSTALL.md for all installation options and configuration.

How to use it

Available as a CLI tool, a GitHub Action, a Tekton Task (OpenShift Pipelines), a Claude Code plugin, and Cursor commands. Each is documented in docs/INSTALL.md.

Cross-component analysis

This is the core differentiator. Most linters check files in isolation. harness-eval builds a component graph that traces data flows across skills, agents, hooks, and MCP servers, then runs cross-component rules against it. This catches classes of issues that per-file analysis cannot:

• A hook reads credentials from env, passes them to a skill, which forwards them to an MCP server with broad network access
• A command's allowed_tools list doesn't cover the tools its instructions actually use
• Settings.json permissions.deny blocks a tool that CLAUDE.md instructs the agent to use
• Two assistants' instruction files (CLAUDE.md and GEMINI.md) have drifted apart
• A skill is defined but never referenced from any instruction file (orphan)

Multi-tool projects are fully supported. When a project uses both Claude Code and Cursor, all components are evaluated together.

Supported AI tools

Inspection rules

92 deterministic rules across 11 categories: structural, frontmatter, content, quality, security, cross-component, commands, CLAUDE.md, MCP, hooks, and agents. Four presets: recommended (default), strict, security, pre-workflow.

For the complete rule list with examples, detection techniques, and framework mappings (OWASP, MITRE ATLAS), see docs/rules-reference.md.

Privacy

harness-lint and harness-security (without --review) are fully offline. LLM review is opt-in: only harness-review, harness-security --review, and skill-review --rubric send snippets to a remote provider (Gemini or Anthropic via CLI, or in-session as a plugin/command).

Before any remote LLM call, likely secrets (tokens, PEM keys, API_KEY= assignments, known prefix patterns) are replaced with [REDACTED] (HE-2). Scans also skip .env, credentials paths, and *.pem / *.key / id_rsa globs by default (HE-3); add more with --exclude.

See docs/how-can-you-know-its-safe-to-use-this-tool.md for details.

Custom YAML rules

Add your own rules without writing Python. Drop a .yaml file in src/harness_eval/inspection/rules/custom/:

id: custom/no-sudo
severity: error
description: Flag sudo usage in skills
suggestion: Remove sudo; skills should not require root access.
target: skill
category: security
patterns:
  - label: sudo command
    regex: '\bsudo\b'
message: "Found '{{label}}' on line {{line}}"

YAML rules support regex pattern matching on component content. Patterns are case-insensitive by default. For complex logic (AST analysis, cross-component checks), use Python rules instead.

Contributing

See CONTRIBUTING.md for adding rules and submitting PRs.

Changelog

See CHANGELOG.md for release history.

Roadmap

See open issues for planned improvements and feature requests.