harness-eval: Command for Claude Code

.cursor/commands/skill-review.md

skill-review is a command for Claude Code, Cursor from redhat-community-ai-tools/harness-eval. It costs 0 tokens per session (596 once invoked), scanned A, original, Apache-2.0.

A command for deeply reviewing one coding-agent skill by checking its files, structure, rules, and fit with the rest of the setup. Static analysis means automated checks of the skill's contents, while qualitative review means human-style assessment of its clarity and usefulness.

In plain words
What is it for?
Use it to evaluate a named skill or skill directory, run the available review checks, read related skill files, and produce a report either in the conversation or in a file.
Why use it?
It turns a skill review into a repeatable process based on the actual files and checks rather than assumptions. This helps uncover missing instructions, contradictions, or unnecessary complexity.

Command for Claude CodeCursor

Written for Claude Code and Cursor: $ARGUMENTS substitution, but also installed under .cursor/. Also seen: mentions CLAUDE.md.

This is redhat-community-ai-tools/harness-eval's own configuration. It tells Claude Code and Cursor how to work on harness-eval itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything harness-eval configures →

Part of the harness-eval plugin — 5 skills, 6 commands shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to redhat-community-ai-tools/harness-eval. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/redhat-community-ai-tools/harness-eval/main/.cursor/commands/skill-review.md
Clone the repo
git clone --depth 1 https://github.com/redhat-community-ai-tools/harness-eval

Made for: Claude Code, Cursor.

Or install harness-eval, the plugin that ships this one along with the rest of its 5 skills, 6 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/redhat-community-ai-tools/harness-eval/skill-review/github.svg)](https://agentmods.dev/commands/redhat-community-ai-tools/harness-eval/skill-review)
Your own site
<a href="https://agentmods.dev/commands/redhat-community-ai-tools/harness-eval/skill-review"><img src="https://agentmods.dev/badge/commands/redhat-community-ai-tools/harness-eval/skill-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/redhat-community-ai-tools/harness-eval/skill-review"><img src="https://agentmods.dev/badge/commands/redhat-community-ai-tools/harness-eval/skill-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 596 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00596
Opus 5 $0.00000 $0.00298
Sonnet 5 $0.00000 $0.00119
Haiku 4.5 $0.00000 $0.00060

Measured 10d ago against content hash 871caa440e3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

skill-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/commands/skill-review.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval Skill

Deep-evaluate a single skill with static analysis and qualitative review, both individually and in context of the full setup.

Arguments

$ARGUMENTS should be the skill name or path to the skill directory.

Hard Rules

  1. Never give a verdict without running the checks and reading the actual content.
  2. Every rubric category must be checked.
  3. Don't manufacture problems. If the skill is good, say so.

Step 1: Ask Output Preference

Ask the user: print the report in conversation, or write to a file?

Step 2: Select the Skill

Determine the skill path from $ARGUMENTS. If the user says a skill name, find it under skills/<name>/SKILL.md or .cursor/skills/<name>/SKILL.md.

Step 3: Run Lint

uvx --from harness-eval harness-eval skill-review <skill-path> --context .

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

Read the output for diagnostics, token count, and contextual findings.

Step 4: Read Actual Files

Read:

  1. The skill's SKILL.md file
  2. All files in the skill's subdirectories (reference files)
  3. All OTHER skill SKILL.md files in the workspace (for context)
  4. System instructions (.cursor/rules/*.mdc, .cursorrules, CLAUDE.md)

Step 5: Qualitative Review

Evaluate the skill against these categories:

  • Specificity: vague platitudes vs actionable patterns
  • Redundancy: duplicates the AI's default behavior?
  • Trigger quality: description missing/broad/narrow?
  • Token efficiency: over 500 lines? Should be split?
  • Instruction clarity: contradictions, vague language, hedging?
  • Content quality: no structure, no examples, missing edge cases?

For each issue found, cite specific evidence from the content.

Step 6: Contextual Analysis

Check redundancy against three sources:

  • The AI's default behavior (generic advice = redundant)
  • Other skills in the workspace (overlap = partially redundant)
  • System instructions content (duplication = wasted tokens)

Read the full file on GitHub · 70 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 70 lines · 0 tokens per session scan A 871caa440e3f

Subscribe to this mod's changes

skill-review is a command published in the GitHub repository redhat-community-ai-tools/harness-eval (27 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 596 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.