Lint

Skill redhat-community-ai-tools/harness-eval/skills/lint

Run deterministic static analysis on the full agent setup (CLAUDE.md, skills, commands, hooks, agents, MCP configs). 97 rules + system-level analysis (token budget, trigger overlaps, dependencies). No LLM. Use when the user wants a fast lint check, CI gate, or structural health report.From its SKILL.md

Install

npx -y skills add redhat-community-ai-tools/harness-eval --skill lint

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

2.4 KB, as published. Nobody here has run it

Lint Setup

Run 97 deterministic rules + system-level analysis on the user's agent setup. No LLM involved. Fast, reproducible, CI-suitable.

Hard Rules

This skill does NOT read files qualitatively. It does NOT apply rubrics. It does NOT run cross-type checks. For that, use /review.
Present the data, don't judge. Report findings as-is. Don't add qualitative commentary.
If everything passes, say so clearly. Don't manufacture problems.

Step 1: Ask Output Preference

Before doing anything else, ask the user:

Where should i present the results?

Terminal - print the report here in the conversation

File - write a markdown report to a file (you'll choose the path)

Wait for their answer before proceeding.

Step 2: Run Static Analysis

Determine the setup path. If the user doesn't specify one, use the current working directory.

uvx --from harness-eval harness-eval harness-lint <setup-path> --format json

If uvx is not available, fall back to pip install harness-eval and use harness-eval directly.

Read the JSON output.

Step 3: Present the Report

Read report-format.md and format the results following that structure.

Include all sections: inventory, token budget, context utilization, trigger analysis, dependencies, findings, and inspection summary.

At the very end of the report, include the exact timing:

Evaluated with: harness-eval v{version} (claude-code-plugin)
Duration: [X minutes Y seconds]

Get {version} by running: uvx --from harness-eval harness-eval --version

Record the timestamp of your first tool call in Step 2 and compute the exact difference when you finish.

If the user chose terminal: print the report in the conversation.

If the user chose file: write the report as markdown to the path they specified (or suggest lint-report.md in the current directory). Tell them the file path when done.