grader

grader is an agent for coding agents from Vibe-Marketer/plugins-and-skills. It costs 250 tokens per session (1,155 once invoked), scanned A, original, MIT.

An evaluation agent for checking whether a skill’s output meets specified expectations or assertions.

In plain words
What is it for?
Use it to grade skill runs, inspect expected and unexpected files, and mark individual requirements as passed or failed.
Why use it?
It removes the need to judge results by appearance alone by checking the original request, execution record, output files, and supporting evidence.

Agent

Part of the create-plugins plugin — 12 skills, 6 commands, 9 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/vibe-marketer/plugins-and-skills/grader
Clone the repo
git clone --depth 1 https://github.com/Vibe-Marketer/plugins-and-skills

Or install create-plugins, the plugin that ships this one along with the rest of its 12 skills, 6 commands, 9 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/vibe-marketer/plugins-and-skills/grader.svg)](https://agentmods.dev/agents/vibe-marketer/plugins-and-skills/grader)
Your own site
<a href="https://agentmods.dev/agents/vibe-marketer/plugins-and-skills/grader"><img src="https://agentmods.dev/badge/agents/vibe-marketer/plugins-and-skills/grader.svg" alt="Measured on agentmods" height="20"></a>
Per session 250 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,155 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00250 $0.01155
Opus 5 $0.00125 $0.00577
Sonnet 5 $0.00050 $0.00231
Haiku 4.5 $0.00025 $0.00115

Measured 4d ago against content hash 3610f49a8072, 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 4d 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.

create-plugins/agents/grader.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

If any input is missing, ask the user before proceeding. </step_1>

<step_2 name="read_transcript"> Read the full execution transcript to understand:

  • What was the original request?
  • What constraints were specified?
  • What should the skill have produced?
  • Were there any mid-execution clarifications or pivots? </step_2>

<step_3 name="examine_outputs"> Read all files in the outputs directory:

  • Catalog every output file (name, size, type)
  • Read content of each file
  • Note any missing expected files
  • Identify any unexpected bonus outputs </step_3>

<step_4 name="evaluate_assertions"> For each assertion in the expectations list:

  1. Interpret: What specifically does this assertion require?
  2. Search: Find relevant evidence in the outputs
  3. Verify: Does the evidence genuinely satisfy the assertion?
  4. Detect surface compliance: Is the output merely mentioning the requirement vs actually fulfilling it?
  5. Verify implicit claims: If the output claims something (e.g., "uses PAS framework"), verify the claim is substantiated
  6. Determine: PASS or FAIL with specific evidence

Apply the burden of proof standard:

  • Clear evidence of fulfillment = PASS
  • Ambiguous or partial evidence = FAIL
  • Surface-level mention without substance = FAIL
  • Genuine implementation with minor imperfections = PASS </step_4>

<step_5 name="compute_results"> Calculate:

  • Total assertions evaluated
  • Pass count and fail count
  • Pass rate (percentage)
  • List of failed assertions with specific reasons </step_5>

<output_format>

Grading Results

Read the full file on GitHub · 143 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. 4d ago First seen · 143 lines · 250 tokens per session scan A 3610f49a8072

Subscribe to this mod's changes

grader is an agent published in the GitHub repository Vibe-Marketer/plugins-and-skills (2 stars, last pushed 6mo ago), licensed MIT. It adds 250 tokens to every session and 1,155 once invoked, about $0.0013 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.