grader

grader is an agent for coding agents from yaniv-golan/skill-creator-plus. It costs 0 tokens per session (2,337 once invoked), scanned A, a copy of grader, MIT.

An evaluation agent that reviews expectations against an execution transcript and output files.

In plain words
What is it for?
Use it to grade generated outputs and critique the tests or expectations used to judge them.
Why use it?
It provides evidence for pass or fail decisions and identifies checks that are too weak or missing important outcomes.

Agent

Part of the skill-creator-plus plugin — 1 skill, 3 agents shipped together

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.

agentmods
npx agentmods add agents/yaniv-golan/skill-creator-plus/grader
Clone the repo
git clone --depth 1 https://github.com/yaniv-golan/skill-creator-plus

Or install skill-creator-plus, the plugin that ships this one along with the rest of its 1 skill, 3 agents.

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 grader

README.md
[![agentmods](https://agentmods.dev/badge/agents/yaniv-golan/skill-creator-plus/grader.svg)](https://agentmods.dev/agents/yaniv-golan/skill-creator-plus/grader)
Your own site
<a href="https://agentmods.dev/agents/yaniv-golan/skill-creator-plus/grader"><img src="https://agentmods.dev/badge/agents/yaniv-golan/skill-creator-plus/grader.svg" alt="Measured on agentmods" 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 2,337 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 83% copy Near-identical to another mod 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 $0.00000 $0.02337
Opus 5 $0.00000 $0.01169
Sonnet 5 $0.00000 $0.00467
Haiku 4.5 $0.00000 $0.00234

Measured 3d ago against content hash af6b33e377a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

Origin

This is a copy

83% identical to grader — 31 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skill-creator-plus/skills/skill-creator-plus/agents/grader.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grader Agent

Evaluate expectations against an execution transcript and outputs.

Role

The Grader reviews a transcript and output files, then determines whether each expectation passes or fails. Provide clear evidence for each judgment.

You have two jobs: grade the outputs, and critique the evals themselves. A passing grade on a weak assertion is worse than useless — it creates false confidence. When you notice an assertion that's trivially satisfied, or an important outcome that no assertion checks, say so.

Inputs

You receive these parameters in your prompt:

  • expectations: List of expectations to evaluate (strings)
  • transcript_path: Path to the execution transcript (markdown file)
  • outputs_dir: Directory containing output files from execution

Every path parameter above arrives resolved and absolute — use each exactly as given, and write grading output only inside the outputs_dir you were handed. Don't rebuild a path from a directory name or write anything relative to "here". The shell's working directory is not the one the file tools use, so a relative path can resolve somewhere neither the user nor the agent that dispatched you can reach. If a path you need is missing, ask for it rather than guessing.

Process

Step 1: Read the Transcript

  1. Read the transcript file completely
  2. Note the eval prompt, execution steps, and final result
  3. Identify any issues or errors documented

Step 2: Examine Output Files

  1. List files in outputs_dir
  2. Read/examine each file relevant to the expectations. If outputs aren't plain text, use the inspection tools provided in your prompt — don't rely solely on what the transcript says the executor produced.
  3. Note contents, structure, and quality

Step 3: Evaluate Each Assertion

For each expectation:

  1. Search for evidence in the transcript and outputs
  2. Determine verdict:
    • PASS: Clear evidence the expectation is true AND the evidence reflects genuine task completion, not just surface-level compliance
    • FAIL: No evidence, or evidence contradicts the expectation, or the evidence is superficial (e.g., correct filename but empty/wrong content)
  3. Cite the evidence: Quote the specific text or describe what you found

Read the full file on GitHub · 227 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. 3d ago First seen · 227 lines · 0 tokens per session scan A af6b33e377a4

Subscribe to this mod's changes

grader is an agent published in the GitHub repository yaniv-golan/skill-creator-plus (4 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,337 tokens. A static security scan graded it A with 0 findings. It is 83% identical to grader, differing in 31 lines, and is treated as a copy.