eval-grader

eval-grader is a skill for Claude Code, Codex from byerlikaya/claude-starter-kit. It costs 62 tokens per session (1,162 once invoked), scanned A, original, MIT.

A testing system for measuring the quality of generated output against a fixed set of tasks and a saved baseline. It combines automatic checks with separate language-model judgments for qualities such as clarity and correctness.

In plain words
What is it for?
Use it when tuning prompts, agents, or generated documents, summaries, slides, interfaces, or extracted data.
Why use it?
It replaces subjective impressions with repeatable scores and can show whether a change improves or harms results, including its cost.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it when tuning prompts, agents, or generated documents, summaries, slides, interfaces, or extracted data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/byerlikaya/claude-starter-kit/eval-grader
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 byerlikaya/claude-starter-kit --skill eval-grader
Clone the repo
git clone --depth 1 https://github.com/byerlikaya/claude-starter-kit

Made for: Claude Code, Codex.

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-grader

README.md
[![agentmods](https://agentmods.dev/badge/skills/byerlikaya/claude-starter-kit/eval-grader/github.svg)](https://agentmods.dev/skills/byerlikaya/claude-starter-kit/eval-grader)
Your own site
<a href="https://agentmods.dev/skills/byerlikaya/claude-starter-kit/eval-grader"><img src="https://agentmods.dev/badge/skills/byerlikaya/claude-starter-kit/eval-grader/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 eval-grader

Your own site · 80×15
<a href="https://agentmods.dev/skills/byerlikaya/claude-starter-kit/eval-grader"><img src="https://agentmods.dev/badge/skills/byerlikaya/claude-starter-kit/eval-grader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,162 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 $0.00062 $0.01162
Opus 5 $0.00031 $0.00581
Sonnet 5 $0.00012 $0.00232
Haiku 4.5 $0.00006 $0.00116

Measured 10d ago against content hash 29aabedc5dbd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

eval-grader 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.

claude-starter/skills/eval-grader/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Eval Grader

Trigger phrases: "eval", "grader", "measure output quality", "LLM-as-judge", "score the output"

Measure every change; don't vibe it. When you iterate on a prompt, an agent, or any generative output (docs, slides, UI, a summary, an extraction), a two-layer grader over a fixed task set turns "feels better" into a signed number you can trust.

This is the external, machine-grounded verifier the iterate skill asks for — a model grading its own output inflates; a separate grader on a fixed suite does not.

Kit adaptation (local, .claude/): use when tuning a generative task; the scorecard goes to docs/EVAL.md (§4.3). Stack-agnostic — graders are ordinary code + judge calls. §4 Prohibitions apply.

Two layers

  • Layer 1 — code graders (deterministic, near-free, run every time): structural metrics over the artifact — did it produce a valid result? plus counts, sizes, schema validity, "wall-of-text" / clutter flags. They catch gross regressions a judge shouldn't be spent on. Ground truth is computed from the source, not hand-authored.
  • Layer 2 — LLM-as-judge graders (semantic): one call per dimension (clarity · correctness-vs-source · completeness…), scored on an explicit rubric. Steer against leniency — "use the full 0-5 range, not only 3-5"; judge with a different model family to avoid self-preference; randomize A/B order to kill position bias.

Each grader is one scorecard column; adding a metric = appending one grader.

pass-slow — grade cost alongside correctness

A result is not just right/wrong. An efficiency grader downgrades a correct output that ran over a turn/token budget to pass-slow — so "correct but too expensive" is visible, not hidden inside a green pass.

Read the full file on GitHub · 78 lines

Files

What ships with it

1 file 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. 10d ago First seen · 78 lines · 62 tokens per session scan A 29aabedc5dbd

Subscribe to this mod's changes

eval-grader is a skill published in the GitHub repository byerlikaya/claude-starter-kit (22 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 1,162 once invoked, about $0.0003 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 2026-08-30.