eval-skill

eval-skill is a skill for Claude Code from redhat-community-ai-tools/harness-eval. It costs 49 tokens per session (927 once invoked), scanned C, original, Apache-2.0.

A detailed review process for checking one agent skill on its own and alongside the rest of an agent setup.

In plain words
What is it for?
Use it to assess whether a specific SKILL.md is well made, useful, compatible with the wider setup, and worth retaining.
Why use it?
It combines fixed rule checks with a careful review of the actual files, helping identify real quality, safety, or redundancy issues before you keep the skill.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

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

Good fit Use it to assess whether a specific SKILL.md is well made, useful, compatible with the wider setup, and worth retaining.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/redhat-community-ai-tools/harness-eval/eval-skill
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add redhat-community-ai-tools/harness-eval --skill eval-skill
Clone the repo
git clone --depth 1 https://github.com/redhat-community-ai-tools/harness-eval

Made for: Claude Code.

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 eval-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/redhat-community-ai-tools/harness-eval/eval-skill.svg)](https://agentmods.dev/skills/redhat-community-ai-tools/harness-eval/eval-skill)
Your own site
<a href="https://agentmods.dev/skills/redhat-community-ai-tools/harness-eval/eval-skill"><img src="https://agentmods.dev/badge/skills/redhat-community-ai-tools/harness-eval/eval-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 927 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00049 $0.00927
Opus 5 $0.00024 $0.00464
Sonnet 5 $0.00010 $0.00185
Haiku 4.5 $0.00005 $0.00093

Measured 8d ago against content hash 2a0f82cbdd55, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

eval-skill scanned grade C with 1 finding 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 8d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- evaluator-ignore: content/broken-references, content/allowed-tools-auto-approve -->
skills/eval-skill/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluate Skill

Deep-evaluate a single skill using lint (deterministic rules) and qualitative review, both individually and in context of the full setup.

Hard Rules

  1. Never give a verdict without running the checks. Read the actual file content and check all rubric categories before assigning a verdict.
  2. Every category must be checked. Both the individual rubric AND the contextual analysis must be fully evaluated.
  3. Read before you judge. Read the actual SKILL.md content (and reference files if they exist).
  4. Don't manufacture problems. If the skill is good, say so. Only report real issues.
  5. Always end with a short summary.
  6. Record the exact start time and compute the exact duration at the end.

Step 1: Ask Output Preference

Before doing anything else, ask the user:

Where should i present the results?

  1. Terminal - print the report here in the conversation
  2. File - write a markdown report to a file (you'll choose the path)

Wait for their answer before proceeding.

Step 2: Select the Skill

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

Step 3: Run Lint (Static Analysis)

Determine the setup context path (usually the current working directory).

uvx --from harness-eval harness-eval skill-review <skill-path> --context <context-path> --format json

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

If no context path, omit the --context flag.

Read the JSON output. It contains diagnostics, token count, and contextual findings. This runs the recommended preset (quality + structural rules). For full security vetting, use /skill-verify instead.

Step 4: Read Actual Files

Read the skill's actual content:

  1. The SKILL.md file
  2. All files in the skill's subdirectories (reference files). Check the COMBINED content.
  3. The skill's guidelines.md (if it exists)

Read the full file on GitHub · 102 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 102 lines · 49 tokens per session scan C 2a0f82cbdd55

Subscribe to this mod's changes

eval-skill is a skill published in the GitHub repository redhat-community-ai-tools/harness-eval (27 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 927 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.