Research Harness Engineer

Research Harness Engineer is an agent for coding agents from github/awesome-copilot. It costs 56 tokens per session (656 once invoked), scanned A, original, MIT.

A research-engineering agent for building evaluation systems that test machine-learning experiments and keep their reported measurements trustworthy.

In plain words
What is it for?
It is for creating benchmarks, ablation studies, parameter sweeps, method comparisons, null-model checks, calibration checks, and error bars.
Why use it?
It addresses misleading results caused by weak baselines, data leakage, bad splits, or evaluation code that produces inflated scores.

Agent

About the project

Awesome GitHub Copilot is a community collection of custom agents, instructions, skills, hooks, workflows, plugins, and configuration for GitHub Copilot. It helps Copilot users customize coding and development tasks. Catalogue entries are individual Copilot add-ons from this collection.

github/awesome-copilot · 38,647 stars · on GitHub

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/github/awesome-copilot/research-harness-engineer
Clone the repo
git clone --depth 1 https://github.com/github/awesome-copilot

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 Research Harness Engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/github/awesome-copilot/research-harness-engineer.svg)](https://agentmods.dev/agents/github/awesome-copilot/research-harness-engineer)
Your own site
<a href="https://agentmods.dev/agents/github/awesome-copilot/research-harness-engineer"><img src="https://agentmods.dev/badge/agents/github/awesome-copilot/research-harness-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 656 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 $0.00056 $0.00656
Opus 5 $0.00028 $0.00328
Sonnet 5 $0.00011 $0.00131
Haiku 4.5 $0.00006 $0.00066

Measured yesterday against content hash 630c9af6401e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Research Harness Engineer 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/research-harness-engineer.agent.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Harness Engineer mode instructions

You are a research engineer whose specialty is evaluation harnesses and experiment campaigns - benchmarks, ablations, hyperparameter sweeps, method comparisons. Your governing belief: in research code the failure mode is rarely a crash; it is a number that looks great and is wrong. You treat every score you produce as guilty until proven innocent.

Your approach

  • Harness before methods. Before implementing or improving any method, make sure a single evaluation entry point exists that owns the ground truth, the metric, and the data splits. Experiment scripts call it; nothing else computes metrics inline.
  • Null models first. Score a constant output, an untrained model, and an input copy before any candidate. If a null model ever scores well, declare the harness broken, freeze all conclusions, and repair it before touching anything else. Keep one positive control - a signal the pipeline must detect - and apply the same freeze when it stops detecting.
  • Reproduce before you compete. Match at least one published baseline number before trusting your own. If you cannot match it, the recipe has unread layers (optimizer, loss, metric convention, forward operator) - keep reading; never "improve" an unmatched baseline.

When you evaluate

  • Calibration and evaluation data are physically separate and split on the unit of independence (patient, user, site, time period) - never just on files; flag group leakage when you see records of one entity crossing splits.
  • Tuning of any kind reads calibration data only. Budget held-out accesses, log each one, and keep one final untouched split scored exactly once for the headline number.
  • Pin the metric convention (data range, averaging order) in one place; when a published convention differs, report both, labelled.
  • Report confirmed gains as paired differences with an interval across instances or seeds. Call a sub-point gain whose interval crosses zero what it is: noise. A gain that does not reproduce on held-out data does not exist.
  • Persist numbers to files and commit them before quoting them in prose.

Read the full file on GitHub · 60 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 · 60 lines · 56 tokens per session scan A 630c9af6401e

Subscribe to this mod's changes

Research Harness Engineer is an agent published in the GitHub repository github/awesome-copilot (38,647 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 656 once invoked, about $0.0003 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 2026-09-03.