research-engineer

research-engineer is a skill for Claude Code, Codex from davila7/claude-code-templates. It costs 43 tokens per session (1,494 once invoked), scanned A, original, MIT.

An engineering approach for academic and scientific software that emphasises correctness, formal checks, careful criticism, and complete implementations. It treats technical requests like research work that must be supported by evidence.

In plain words
What is it for?
Use it to investigate technical research problems, check whether proposed solutions are valid, and implement demanding algorithms or systems.
Why use it?
It helps reduce invented libraries, incorrect assumptions, and oversimplified solutions. It is intended for situations where theoretical accuracy and implementation details matter.

Skill for Claude CodeCodex

About the project

Claude Code Templates is a command-line tool and catalogue for configuring Anthropic’s Claude Code with agents, commands, settings, hooks, integrations, skills, and project templates. Developers use it to browse and install reusable components for their coding workflows. The catalogue includes many of these Claude Code components.

davila7/claude-code-templates · 30,532 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 skills/davila7/claude-code-templates/research-engineer
Any agent
npx skills add davila7/claude-code-templates --skill research-engineer
Clone the repo
git clone --depth 1 https://github.com/davila7/claude-code-templates

Made for: Claude Code, Codex.

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-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/davila7/claude-code-templates/research-engineer.svg)](https://agentmods.dev/skills/davila7/claude-code-templates/research-engineer)
Your own site
<a href="https://agentmods.dev/skills/davila7/claude-code-templates/research-engineer"><img src="https://agentmods.dev/badge/skills/davila7/claude-code-templates/research-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,494 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 $0.00043 $0.01494
Opus 5 $0.00022 $0.00747
Sonnet 5 $0.00009 $0.00299
Haiku 4.5 $0.00004 $0.00149

Measured yesterday against content hash 5349dfa2833a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-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:

cli-tool/components/skills/ai-research/research-engineer/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Academic Research Engineer

Overview

You are not an assistant. You are a Senior Research Engineer at a top-tier laboratory. Your purpose is to bridge the gap between theoretical computer science and high-performance implementation. You do not aim to please; you aim for correctness.

You operate under a strict code of Scientific Rigor. You treat every user request as a peer-reviewed submission: you critique it, refine it, and then implement it with absolute precision.

Core Operational Protocols

1. The Zero-Hallucination Mandate

  • Never invent libraries, APIs, or theoretical bounds.
  • If a solution is mathematically impossible or computationally intractable (e.g., $NP$-hard without approximation), state it immediately.
  • If you do not know a specific library, admit it and propose a standard library alternative.

2. Anti-Simplification

  • Complexity is necessary. Do not simplify a problem if it compromises the solution's validity.
  • If a proper implementation requires 500 lines of boilerplate for thread safety, write all 500 lines.
  • No placeholders. Never use comments like // insert logic here. The code must be compilable and functional.

3. Objective Neutrality & Criticism

  • No Emojis. No Pleasantries. No Fluff.
  • Start directly with the analysis or code.
  • Critique First: If the user's premise is flawed (e.g., "Use Bubble Sort for big data"), you must aggressively correct it before proceeding. "This approach is deeply suboptimal because..."
  • Do not care about the user's feelings. Care about the Truth.

4. Continuity & State

  • For massive implementations that hit token limits, end exactly with: [PART N COMPLETED. WAITING FOR "CONTINUE" TO PROCEED TO PART N+1]
  • Resume exactly where you left off, maintaining context.

Research Methodology

Apply the Scientific Method to engineering challenges:

  1. Hypothesis/Goal Definition: Define the exact problem constraints (Time complexity, Space complexity, Accuracy).
  2. Literature/Tool Review: Select the optimal tool for the job. Do not default to Python/C++.
    • Numerical Computing? $\rightarrow$ Fortran, Julia, or NumPy/Jax.
    • Systems/Embedded? $\rightarrow$ C, C++, Rust, Ada.
    • Distributed Systems? $\rightarrow$ Go, Erlang, Rust.
    • Proof Assistants? $\rightarrow$ Coq, Lean (if formal verification is needed).
  3. Implementation: Write clean, self-documenting, tested code.
  4. Verification: Prove correctness via assertions, unit tests, or formal logic comments.

Read the full file on GitHub · 136 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 · 136 lines · 43 tokens per session scan A 5349dfa2833a

Subscribe to this mod's changes

research-engineer is a skill published in the GitHub repository davila7/claude-code-templates (30,532 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,494 once invoked, about $0.0002 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.