compound-science CLAUDE.md

compound-science CLAUDE.md is an instructions file for coding agents from James-Traina/compound-science. It costs 2,386 tokens per session, scanned A, original, MIT.

Repository instructions for the compound-science project, an AI-assisted research toolkit for quantitative social science. They describe a repeatable path from research ideas through planning, implementation, review, and reusable documentation.

In plain words
What is it for?
Use them to brainstorm research, create plans, run work with quality checks, request reviews from specialist perspectives, and save reusable research solutions.
Why use it?
They give contributors and coding assistants shared rules for organizing research work and checking its quality. Quantitative social science uses data and statistical methods to study social and economic questions.

Instructions file

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 instructions/james-traina/compound-science/claude-md
Clone the repo
git clone --depth 1 https://github.com/James-Traina/compound-science

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 compound-science CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/james-traina/compound-science/claude-md.svg)](https://agentmods.dev/instructions/james-traina/compound-science/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/james-traina/compound-science/claude-md"><img src="https://agentmods.dev/badge/instructions/james-traina/compound-science/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,386 This file is loaded in full into every session.
When invoked 2,386 The same file — it is already loaded in full.
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 $0.02386 $0.02386
Opus 5 $0.01193 $0.01193
Sonnet 5 $0.00477 $0.00477
Haiku 4.5 $0.00239 $0.00239

Measured 4d ago against content hash 1176edb736f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compound-science CLAUDE.md 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 4d 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.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

compound-science Plugin

AI-powered research tools for quantitative social science: structural econometrics, causal inference, game theory, applied micro, and reproducible pipelines. Built on the compound workflow principle: each unit of research work makes subsequent work easier.

Core Workflow

Brainstorm → Plan → Work → Review → Compound → Repeat

  1. /workflows:brainstorm — Explore research approaches, compare methods, pick one. Writes to docs/brainstorms/.
  2. /workflows:plan — Create an implementation plan from the brainstorm. Writes to docs/plans/.
  3. /workflows:work — Execute the plan with quality gates and convergence monitoring.
  4. /workflows:review — Multi-agent parallel review (econometric-reviewer, numerical-auditor, identification-critic, journal-referee).
  5. /workflows:compound — Extract reusable solutions into docs/solutions/ by category.

Each step has an interactive handoff offering the next step. Use /lfg to chain all five automatically, or /slfg for parallel swarm execution. Ideate (/workflows:ideate) is an optional divergent pre-step before brainstorming.

Skills (20)

Workflow (6) — core research loop

  • /workflows:ideate, /workflows:brainstorm, /workflows:plan, /workflows:work, /workflows:review, /workflows:compound

Chain (2) — automated multi-step execution

  • /lfg — Sequential: brainstorm → plan → work → review → compound (with hard gates)
  • /slfg — Parallel swarm variant of /lfg

Wrappers (2) — thin routing skills

  • /estimate — Routes to /workflows:work with estimation pipeline context from empirical-playbook
  • /replicate — Routes to reproducibility-auditor agent

Domain knowledge (10) — reusable reference skills

  • structural-modeling — NFXP, MPEC, BLP, dynamic discrete choice, auction models
  • causal-inference — IV/2SLS/GMM, DiD, RDD, synthetic control, matching
  • causal-ml — Double ML, causal forests (GRF), DR-Learner, post-LASSO, high-dimensional controls
  • game-theory — Nash/SPE/BNE equilibria, entry models, conduct testing, bargaining, multiple equilibria
  • identification-proofs — Formal identification arguments: target parameter → model → rank conditions → regularity conditions
  • bayesian-estimation — MCMC, Stan/PyMC/Numpyro, prior elicitation, MCMC diagnostics, Bayesian structural models
  • reproducible-pipelines — Makefile/Snakemake/DVC, Stata pipelines, environment management, replication standards
  • empirical-playbook — Method selection, diagnostics by method, power analysis, estimation pipeline, sensitivity analysis, data acquisition (FRED/World Bank)
  • publication-output — Publication-quality tables and figures: stargazer-style tables, event study plots, RD plots, specification curves
  • submission-guide — Pre-submission checklists, journal-specific formatting for 20+ journals, referee response strategy and templates

Read the full file on GitHub · 144 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. 4d ago First seen · 144 lines · 2,386 tokens per session scan A 1176edb736f0

Subscribe to this mod's changes

compound-science CLAUDE.md is an instructions file published in the GitHub repository James-Traina/compound-science (13 stars, last pushed 5mo ago), licensed MIT. It adds 2,386 tokens to every session, about $0.0119 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 2026-08-30.

Related

Other instructions, from other repositories

bio-gene-to-reference-tree copilot-instructions.md

Copilot instructions for Hongda-Zhao/bio-gene-to-reference-tree, a project described as: Auditable agent skill for resolving protein queries, selecting references, and planning reproducible phylogenetic trees.

Hongda-Zhao/bio-gene-to-reference-tree · 105 tokens

braina GEMINI.md

Instructions for brainets/braina, covering project: braina (brain interaction analysis), 1. project context & purpose, 2. commands, verify environment (all core dependencies) and run the verification test suite for frites + hoi.

brainets/braina · 1,269 tokens

research-automation CLAUDE.md

Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.

lucafusarbassini/research-automation · 904 tokens

shannon-prover CLAUDE.md

Claude Code instructions for SkyShannonProver/shannon-prover, covering shannon prover: claude entry point, current boundary, easycrypt environment, eval safety and current documentation.

SkyShannonProver/shannon-prover · 586 tokens

SciCrucible CLAUDE.md

Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.

Xinyang-Li666/SciCrucible · 1,107 tokens

torchcell CLAUDE.md

Claude Code instructions for Mjvolk3/torchcell, covering vision -- the virtual cell (north star), for local configs, git worktrees, programming guide and provenance & reproducibility.

Mjvolk3/torchcell · 12,957 tokens