{"repo":"redhat-community-ai-tools/harness-eval","free":true,"listed":false,"github":"https://github.com/redhat-community-ai-tools/harness-eval","clone":"git clone https://github.com/redhat-community-ai-tools/harness-eval.git","description":"Evaluate (lint, review, and security-audit) your AI coding agent harness.","language":"Python","stars":25,"topics":["ai","claude-code","code-agent","cursor","evaluation","harness","copilot","gemini-cli","opencode","github-actions"],"license":"Apache-2.0","category":"cli-tools","readme_excerpt":"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, Codex CLI), builds a component graph across all of them, and runs 97 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/ , .codex/ . Quick start Example output: 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 , Cursor commands , and a pre-commit hook . Each is documented in docs/INSTALL.md . Suppressing findings Not every finding is a real problem. Four ways to handle false positives: Inline suppression (per-file or per-line): Baseline (incremental adoption): Exclude files : --exclude \"vendor/ \" --exclude \".git/ \" (repeatable). Advisory mode : --enforce advisory reports findings without failing CI. See docs/rules-reference.md for rule confidence tiers (exact, heuristic, advisory). Command What it does LLM needed? --------- ------------- ------------- harness-lint 97 deterministic rules + system analysis (token budget, t","default_branch":null,"files":null,"tree":[],"storefront":"/r/redhat-community-ai-tools","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/redhat-community-ai-tools/harness-eval/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}