eval-skill

eval-skill is a command for Claude Code from shennawardana23/skillme. It costs 16 tokens per session (227 once invoked), scanned A, original, Apache-2.0.

A command for validating a skill and running its evaluation tests with smeval, a tool that checks expected behavior against test cases.

In plain words
What is it for?
Use it to validate a skill, run its benchmark cases, inspect pass or fail results, and locate the generated HTML report and feedback file.
Why use it?
It combines the validation and evaluation steps and reports the evidence needed to judge whether the skill works correctly.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the skillme plugin — 137 skills, 2 commands shipped together

Good fit Use it to validate a skill, run its benchmark cases, inspect pass or fail results, and locate the generated HTML report and feedback file.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/shennawardana23/skillme/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.

Clone the repo
git clone --depth 1 https://github.com/shennawardana23/skillme

Made for: Claude Code.

Or install skillme, the plugin that ships this one along with the rest of its 137 skills, 2 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/commands/shennawardana23/skillme/eval-skill.svg)](https://agentmods.dev/commands/shennawardana23/skillme/eval-skill)
Your own site
<a href="https://agentmods.dev/commands/shennawardana23/skillme/eval-skill"><img src="https://agentmods.dev/badge/commands/shennawardana23/skillme/eval-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 227 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 $0.00016 $0.00227
Opus 5 $0.00008 $0.00113
Sonnet 5 $0.00003 $0.00045
Haiku 4.5 $0.00002 $0.00023

Measured 8d ago against content hash 3e6b22cc7841, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

eval-skill 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 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.

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.

.claude/commands/eval-skill.md · 19 lines

What it actually says

Run the full eval loop for skill $ARGUMENTS and report back:

  1. go build -o smeval ./cmd/smeval (skip if ./smeval is already newer than cmd/smeval/ and internal/).
  2. uvx --from skills-ref agentskills validate skills/$ARGUMENTS
  3. ./smeval validate skills/$ARGUMENTS
  4. ./smeval run skills/$ARGUMENTS -benchmark
  5. Report pass/fail per case with the quoted assertion evidence, the report.html path, and the feedback.json path — tell the user to open and fill in feedback.json before treating the run as done (see TESTING.md's "Reviewing results with a human" section).

If $ARGUMENTS is empty, ask which skill (a directory under skills/) to run before doing anything else.

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 · 19 lines · 16 tokens per session scan A 3e6b22cc7841

Subscribe to this mod's changes

eval-skill is a command published in the GitHub repository shennawardana23/skillme (2 stars, last pushed 10d ago), licensed Apache-2.0. It adds 16 tokens to every session and 227 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.