What is ReactiveDynamics.jl AGENTS.md?

Repository instructions for ReactiveDynamics.jl, a Julia engine for timed, random, resource-limited process models. They explain where the agent layer lives, which documents to read first, and how models are validated.

Use them when working on the repository to find the relevant agent skills, understand its JSON model format, follow the project setup, and validate changes.

They give coding agents project-specific orientation and safety boundaries before they edit files. They also identify validation as the trust boundary for model changes.

How Merck/ReactiveDynamics.jl configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Merck/ReactiveDynamics.jl. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Merck/ReactiveDynamics.jl/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Merck/ReactiveDynamics.jl

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/merck/reactivedynamics.jl/agents-md/github.svg)](https://agentmods.dev/instructions/merck/reactivedynamics.jl/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/merck/reactivedynamics.jl/agents-md"><img src="https://agentmods.dev/badge/instructions/merck/reactivedynamics.jl/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/merck/reactivedynamics.jl/agents-md"><img src="https://agentmods.dev/badge/instructions/merck/reactivedynamics.jl/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,173 This file is loaded in full into every session.

When invoked 1,173 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01173	$0.01173
Opus 5.5	$0.00469	$0.00469
Sonnet 5.5	$0.00235	$0.00235
Haiku 4.5	$0.00117	$0.00117

Measured 2d ago against content hash 79b006ef8cde, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ReactiveDynamics.jl AGENTS.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 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.

AGENTS.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Orientation for a coding agent working in this repository: Codex, Jules, Cursor, Gemini CLI, or anything else that reads an AGENTS.md. Claude Code reads CLAUDE.md instead, which carries the same facts plus the engine's internals.

What this is

ReactiveDynamics.jl is a Julia engine for timed, stochastic, resource-constrained process models: business and R&D processes, not chemistry, despite the reaction-network notation. agent/ is a skill layer on top of it that carries a user from a business question to a defensible number. Models are JSON documents (*.rdj.json), never Julia source; the eval-free validate pass is the trust boundary.

Start here

Read agent/README.md, then agent/skills/rd-study/SKILL.md, the orchestrator. It runs four phases (FRAME → AUTHOR → DIAGNOSE → REPORT) and reads one phase skill at a time.
A skill named in the text (rd-frame, rd-author, rd-doctor, rd-report) lives at agent/skills/<name>/SKILL.md. Skills are plain Markdown playbooks: the YAML header is metadata, and everything they ask you to do is a shell command.
The authoring vocabulary is agent/reference/model_schema.md, generated from the source and never edited by hand. agent/studies/portfolio_bid/model.rdj.json is a pure-data model to copy as a starting point.

Setup

Julia ≥ 1.12 (juliaup is the easiest install), then once: julia --project=. -e 'using Pkg; Pkg.instantiate()'. Use Julia 1.12 to reproduce published numbers: ensemble member seeds derive from Julia's hash, which changes between versions, so on 1.13 every ensemble and effect result shifts (the known answer moves from 18.99 ± 2.53 to 24.06 ± 2.50 — compatible, not identical) and acceptance.jl fails. From the repo root, juliaup add 1.12 && juliaup override set 1.12 makes julia resolve to 1.12 in this directory only (charter W31). Expect several minutes on a fresh machine, mostly precompilation. No Manifest.toml is committed, so dependency versions resolve fresh; CI tests both the latest compatible versions and the declared lower bounds.
Optional: Graphviz (dot) for rdx draw, which writes a .dot file without it; Python ≥ 3.8, standard library only, for the launch_supply helper scripts.
The commands below are bash. On Windows use WSL, or run the same julia invocations from PowerShell; Julia itself is cross-platform.

Read the full file on GitHub · 35 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.

2d ago First seen · 35 lines · 1,173 tokens per session scan A 79b006ef8cde

Subscribe to this mod's changes

ReactiveDynamics.jl AGENTS.md is an instructions file published in the GitHub repository Merck/ReactiveDynamics.jl (17 stars, last pushed 27d ago), licensed MIT. It adds 1,173 tokens to every session, about $0.0047 per session on Opus 5.5. 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 2026-11-07.

Building agents Scientific agent-based-modeling decision-making discrete-event-simulation julia julia-language petri-nets

ReactiveDynamics.jl AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ReactiveDynamics.jl AGENTS.mdMerck/ReactiveDynamics.jl	Instructions file	17	27d ago	MIT	A	1,173	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

ReactiveDynamics.jl: Instructions file for Codex