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.
curl -O https://raw.githubusercontent.com/Merck/ReactiveDynamics.jl/main/CLAUDE.mdgit clone --depth 1 https://github.com/Merck/ReactiveDynamics.jlWrote 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/merck/reactivedynamics.jl/claude-md)<a href="https://agentmods.dev/instructions/merck/reactivedynamics.jl/claude-md"><img src="https://agentmods.dev/badge/instructions/merck/reactivedynamics.jl/claude-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.
<a href="https://agentmods.dev/instructions/merck/reactivedynamics.jl/claude-md"><img src="https://agentmods.dev/badge/instructions/merck/reactivedynamics.jl/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.03491 | $0.03491 |
| Opus 5.5 | $0.01396 | $0.01396 |
| Sonnet 5.5 | $0.00698 | $0.00698 |
| Haiku 4.5 | $0.00349 | $0.00349 |
Grade A, and why
ReactiveDynamics.jl 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 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — ReactiveDynamics.jl agent guide
Agent-facing orientation for the ref-agents branch. Re-verify any file:line before acting — line numbers drift; grep to confirm.
What this project is
ReactiveDynamics.jl (RD) is a timed, stochastic, resource-constrained Petri net / discrete-event engine for system-dynamics-style modeling of business / R&D processes (budgeting, ledgers, what-if, rNPV) — NOT a chemical reaction network, despite the Catalyst-derived DSL surface. A transition is a stateful recipe that spawns in-flight instances at a Poisson rate, occupies shared finite resource pools (places) over a cycle time, and completes with a terminal probability-of-success that emits RHS products. Resources carry a modality governing allocation (:nonblock/:conserved/:rate), and a cost/reward/valuation ledger accumulates into a per-step log. Structured/agentic tokens are first-class entities (a "project" is an agent with attributes, custom behavior, and history) that can be instantiated, selected by predicate, advanced through lifecycle phases, and audited per-program. RD is part of the DyVE family and sits ON TOP of AlgebraicAgents.jl (AA): a ReactionNetworkProblem IS an AA @aagent, so a network is a node in a larger heterogeneous AA hierarchy.
Where the durable spec lives
The durable engineering artifacts live under top-level spec/, kept separate from docs/ — which is reserved for the Documenter.jl static-pages site (docs/make.jl, docs/src/, generated docs/build/). Do not put spec material in docs/.
spec/STATUS.md is the single entry point — start there. It carries the authoritative catalog of every durable artifact (CONTRACT_DRAFT, adr/, PR_DRAFT, DOCS_CHARTER, INVENTORY, the retired/archived docs) so this guide need not duplicate it. The three you touch most:
spec/STATUS.md— "what is the state, what is left." The dashboard: feature→commit table, test tally, deferred items with gates.spec/CONTRACT_DRAFT.md— the normative operational-semantics spec (§1–§15). The durable spine: what the engine must do.spec/INVENTORY.md— the current-source map (module map, public-API audit, static store, stepping trace, AA touchpoints): where it lives in the source.spec/adr/— Architecture Decision Records (append-only), status table inspec/adr/README.md. To change a decision, add a new ADR; do not rewrite history.
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 · 64 lines · 3,491 tokens per session scan A fb13c8bd3b85
ReactiveDynamics.jl CLAUDE.md is an instructions file published in the GitHub repository Merck/ReactiveDynamics.jl (17 stars, last pushed 27d ago), licensed MIT. It adds 3,491 tokens to every session, about $0.0140 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.
ReactiveDynamics.jl CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ReactiveDynamics.jl CLAUDE.mdMerck/ReactiveDynamics.jl | Instructions file | 17 | 27d ago | MIT | A | 3,491 | Claude Code |
| 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 |