grader

An evaluation tool that checks whether expected results were achieved by reviewing an agent's conversation record and produced files.

In plain words
What is it for?
Use it to assess coding-agent runs, inspect their output files, and identify gaps in the expectations used to judge them.
Why use it?
It replaces informal checking with evidence for each pass or failure, while also revealing tests that are too weak or missing important outcomes.

Agent

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/matrixfounder/agentic-development/grader
Clone the repo
git clone --depth 1 https://github.com/MatrixFounder/Agentic-development
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 1,333 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 $0.00000 $0.01333
Opus 5 $0.00000 $0.00666
Sonnet 5 $0.00000 $0.00267
Haiku 4.5 $0.00000 $0.00133

Measured yesterday against content hash 8e5f61f2d7ef, 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 yesterday.

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.

.agent/skills/skill-creator/agents/grader.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 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.

[!NOTE] Adapted from Anthropic's Grader Agent. Vendor-agnostic — works with any LLM.

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

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

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
  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, contradicts expectation, or evidence is superficial
  3. Cite the evidence: Quote the specific text or describe what you found

Step 4: Extract and Verify Claims

Beyond predefined expectations, extract implicit claims from the outputs:

  1. Factual claims ("The form has 12 fields") → verify against outputs
  2. Process claims ("Used pypdf to fill the form") → verify from transcript
  3. Quality claims ("All fields filled correctly") → evaluate if justified
  4. Flag unverifiable claims — note claims that cannot be verified

Read the full file on GitHub · 125 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. yesterday First seen · 125 lines · 0 tokens per session scan A 8e5f61f2d7ef

Subscribe to this mod's changes

grader is an agent published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 18d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,333 tokens. 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.