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.
npx agentmods add instructions/james-traina/compound-science/claude-mdgit clone --depth 1 https://github.com/James-Traina/compound-scienceWrote 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.
[](https://agentmods.dev/instructions/james-traina/compound-science/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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
/workflows:brainstorm— Explore research approaches, compare methods, pick one. Writes to docs/brainstorms/./workflows:plan— Create an implementation plan from the brainstorm. Writes to docs/plans/./workflows:work— Execute the plan with quality gates and convergence monitoring./workflows:review— Multi-agent parallel review (econometric-reviewer, numerical-auditor, identification-critic, journal-referee)./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:workwith estimation pipeline context fromempirical-playbook/replicate— Routes toreproducibility-auditoragent
Domain knowledge (10) — reusable reference skills
structural-modeling— NFXP, MPEC, BLP, dynamic discrete choice, auction modelscausal-inference— IV/2SLS/GMM, DiD, RDD, synthetic control, matchingcausal-ml— Double ML, causal forests (GRF), DR-Learner, post-LASSO, high-dimensional controlsgame-theory— Nash/SPE/BNE equilibria, entry models, conduct testing, bargaining, multiple equilibriaidentification-proofs— Formal identification arguments: target parameter → model → rank conditions → regularity conditionsbayesian-estimation— MCMC, Stan/PyMC/Numpyro, prior elicitation, MCMC diagnostics, Bayesian structural modelsreproducible-pipelines— Makefile/Snakemake/DVC, Stata pipelines, environment management, replication standardsempirical-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 curvessubmission-guide— Pre-submission checklists, journal-specific formatting for 20+ journals, referee response strategy and templates
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.
- 4d ago First seen · 144 lines · 2,386 tokens per session scan A 1176edb736f0
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.
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.
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.
research-automation CLAUDE.md
Instructions for lucafusarbassini/research-automation, covering ricet - research automation framework, project overview, claude-flow mcp, workflow habits and file organization.
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.
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.
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.