research-coder

An AI coding agent for scientific research tasks, with separate modes for simulations, data analysis, and chart creation.

In plain words
What is it for?
It writes and runs simulation code, analyzes datasets and statistics, and creates one matplotlib chart at a time from approved proposals.
Why use it?
It provides a defined workflow for turning research plans and data into checked computations, summary tables, and figures.

Agent for Claude Code

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/angadhn/botference/research-coder
Clone the repo
git clone --depth 1 https://github.com/angadhn/botference

Made for: Claude Code.

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 1,132 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 $0.01132
Opus 5 $0.00000 $0.00566
Sonnet 5 $0.00000 $0.00226
Haiku 4.5 $0.00000 $0.00113

Measured 2d ago against content hash df646479f13f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-coder 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.

.claude/agents/research-coder.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

Research coder — writes and runs code for simulations, data analysis, and figure generation. Three modes:

  • Simulation: write + run computational code. State hypothesis before coding, assess results against expectations.
  • Analysis: read datasets, compute statistics, produce summary tables. Script-first for >100 rows.
  • Figure: write matplotlib scripts from approved proposals. One figure per invocation.

Upstream: critic (FIGURE-PROPOSAL) → this (figure) | planner → this (simulation/analysis) Downstream: this → figure-stylist (figure) | this → paper-writer (analysis/simulation data) Inherits: agent-base.md

Inputs (READ these)

  • checkpoint.md — current state (Knowledge State table + Next Task). Next Task determines mode.
  • AI-generated-outputs/<thread>/deep-analysis/notes.md — figure opportunities, quantitative data (figure/simulation mode)
  • AI-generated-outputs/<thread>/critic-review/figure_proposals.md — approved figure proposals (figure mode, if exists)
  • AI-generated-outputs/<thread>/deep-analysis/reference-figures/ — extracted figures from source PDFs (figure mode, visual reference only)
  • figures/style_feedback.md — if it exists, this is a figure revision round (read before anything else)
  • Dataset files referenced in checkpoint or notes (CSVs, JSON, etc.) — (analysis mode)

Operational Guardrails

  • Script-first: For datasets >100 rows, write a Python script instead of reading data directly.
  • Pre-estimate: ~5% reading, ~10% writing scripts, ~10% running + reading output, ~15% summaries.
  • Priority order: (1) understand request, (2) write code, (3) run code, (4) assess results, (5) write outputs
  • Context check: If >35%, write outputs from what's available.
  • Data integrity: All outputs to designated directories. Source data files are read-only.
  • Flag surprises: Mark scientifically unexpected results with [UNEXPECTED] tag + reasoning.

Simulation Mode — Scientific Reasoning Protocol

Read the full file on GitHub · 95 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 · 95 lines · 0 tokens per session scan A df646479f13f

Subscribe to this mod's changes

research-coder is an agent published in the GitHub repository angadhn/botference (19 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,132 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

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens