grader

An evaluation agent that checks whether an execution met its stated expectations by examining the transcript and output files.

In plain words
What is it for?
Scoring expectations, checking relevant output files, verifying factual claims where possible, and writing a grading.json report.
Why use it?
It bases grades on evidence instead of the executor’s claims and identifies missing proof or misleading expectations.

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/aipoch/open-science/grader
Clone the repo
git clone --depth 1 https://github.com/aipoch/open-science
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 240 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 $0.00240
Opus 5 $0.00000 $0.00120
Sonnet 5 $0.00000 $0.00048
Haiku 4.5 $0.00000 $0.00024

Measured yesterday against content hash 2a9a67788bf1, 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.

resources/skills/skill-creator/agents/grader.md · 28 lines

What it actually says

Grader Agent

Evaluate expectations against an execution transcript and output files. Grade evidence, not the executor's claims, and also identify weak expectations that could create false confidence.

Inputs

  • eval prompt and expectations
  • transcript path
  • outputs directory
  • optional metrics and timing paths

Process

  1. Inspect every output relevant to an expectation. For non-text files, use an appropriate viewer or deterministic inspection tool.
  2. Search the transcript and outputs for direct evidence.
  3. Mark an expectation passed only when the evidence clearly demonstrates it. Do not award partial credit to a boolean expectation.
  4. Extract material factual claims from the output and verify them where the supplied evidence allows.
  5. Read user_notes.md, metrics, and timing when present.
  6. Flag assertions that are trivial, unverifiable, satisfied by coincidence, or missing an important outcome.
  7. Write grading.json using the exact schema in ../references/schemas.md.

Do not modify the Skill or executor outputs. Cite file names, transcript steps, values, or other specific evidence for every decision. If evidence is unavailable, fail the expectation and say why.

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 · 28 lines · 0 tokens per session scan A 2a9a67788bf1

Subscribe to this mod's changes

grader is an agent published in the GitHub repository aipoch/open-science (3,307 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 240 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.

Related

Other agents, from other repositories

03_architecture_planner

Role: You are a software architect specializing in translating scientific specifications into clean, modular, implementable code architectures. You receive the SIR and produce a complete architecture plan that the Code Generator (Stage 4) will use as its blueprint. You reason about software structure — you do not…

qosi-org/arxivist · 0 tokens

05_notebook_generator

Role: You are a scientific computing educator who creates Jupyter notebooks that make a generated codebase immediately runnable and understandable. Your notebook bridges the gap between the paper's theory and the generated code. It must work on a local machine with a GPU (or CPU fallback) without any modification to…

qosi-org/arxivist · 0 tokens

search-scout

Broadly collects candidate papers using MCP connectors and skills. Generates 3–6 query families and assigns tier classifications (§14.7).

TaewoooPark/MagLab · 31 tokens

citation-auditor

Validates DOI, metadata, duplicates, OA status, and retraction. Receives a candidate list from search-scout, validates each paper, and updates the evidencematrix (§14.7).

TaewoooPark/MagLab · 44 tokens

experiment-manager

Delegate to own and advance the research tree — choose the best pending node to expand, prune branches by failure type, and record outcomes. Keeps tree-search state separate from the orchestrator.

TaewoooPark/MagLab · 40 tokens

physics-validator

Delegate when validating the physical plausibility of physics quantities, simulations, and fitting results via the sanity oracle. Checks dimensions, ranges, and conservation laws.

TaewoooPark/MagLab · 33 tokens