grader

An evaluator that compares expected results with an execution transcript and the files produced by an agent or program.

In plain words
What is it for?
It helps read execution logs, inspect output files, judge expectations as pass or fail, explain the evidence, and review the quality of the evaluation itself.
Why use it?
It provides evidence for deciding whether each requirement was met and can expose evaluation criteria that are too easy or miss 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/smixs/skill-conductor/grader
Clone the repo
git clone --depth 1 https://github.com/smixs/skill-conductor
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 3,017 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 $0.03017
Opus 5 $0.00000 $0.01509
Sonnet 5 $0.00000 $0.00603
Haiku 4.5 $0.00000 $0.00302

Measured 2d ago against content hash b72b59dc7e35, 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 2d 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.

skills/skill-conductor/agents/grader.md · 256 lines

How it starts

The opening of the file, as written. The whole thing — 256 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. First, grade the outputs: for every expectation you write a critique of the evidence BEFORE you commit to pass/fail (Step 3). Second, critique the eval SET as a whole once grading is done (Step 6) — a passing grade on a weak assertion is worse than useless, so when an assertion is trivially satisfied or an important outcome goes unchecked, 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

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: Frame Expectations as Binary Questions (BinEval)

Each expectation is a GENERATED binary yes/no question: "yes" (passed=true) means the criterion is satisfied, "no" (passed=false) means it is violated. Derive them with the two-step meta-prompt:

  1. Summarize — turn the eval target (the prompt + the outputs it should produce) into explicit requirements R = {r1..rK}, each a distinct, checkable criterion. The supplied expectations are your starting requirements; tighten any that are vague.
  2. Decompose — for each requirement, emit at least one binary question whose "yes" = satisfied and "no" = violated, paired with a concise violation example.

Read the full file on GitHub · 256 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. 2d ago First seen · 256 lines · 0 tokens per session scan A b72b59dc7e35

Subscribe to this mod's changes

grader is an agent published in the GitHub repository smixs/skill-conductor (163 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,017 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 2026-08-30.