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/cogswellspacely8-star/simengine/claude-mdgit clone --depth 1 https://github.com/cogswellspacely8-star/simengineWrote 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/cogswellspacely8-star/simengine/claude-md)<a href="https://agentmods.dev/instructions/cogswellspacely8-star/simengine/claude-md"><img src="https://agentmods.dev/badge/instructions/cogswellspacely8-star/simengine/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 | $0.02254 | $0.02254 |
| Opus 5 | $0.01127 | $0.01127 |
| Sonnet 5 | $0.00451 | $0.00451 |
| Haiku 4.5 | $0.00225 | $0.00225 |
Grade A, and why
simengine CLAUDE.md scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`v3/feeds/` (real-time data adapters like Polymarket Gamma) and `v3/llm/` (the natural-language front door) are also opt-in and network-touching, but stay inside the stdlib promise — they use only `urllib`. The core engi How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — SimEngine
What this is
A domain-agnostic Monte Carlo simulation and decision intelligence system. Define variables, logic, and risk tolerances in JSON; the engine simulates thousands of futures and (optionally) evolves toward strategies that respect safety constraints. Used both as a standalone web UI and as an MCP/HTTP tool for AI agents.
Open-core licensed. The engine in this repo is Apache 2.0. The hosted MCP service is commercial (see LICENSE-COMMERCIAL.md). Don't conflate the two when modifying licenses or deployment guidance.
Hard constraint: zero Python dependencies
The default engine uses only the Python standard library. This is a load-bearing design choice — it means SimEngine runs anywhere Python 3.8+ runs, no pip install required. Do not add requirements.txt entries or import statements that pull external packages into v3/*.py. If you think you need a third-party lib, you almost certainly don't — check kernel.py and bayesian.py for the pattern.
The Rust acceleration crates under crates/ are the only exception, and they're explicitly opt-in — the Python code falls back gracefully when simengine_native isn't importable.
v3/feeds/ (real-time data adapters like Polymarket Gamma) and v3/llm/ (the natural-language front door) are also opt-in and network-touching, but stay inside the stdlib promise — they use only urllib. The core engine never imports them. Treat any new feed as opt-in and ToS-careful: market data is an internal simulation input, never a rebroadcast feed or trade signal. The llm/ module turns a question into a config via a draft→validate→repair loop; the engine's own validate_config (in validation.py) grounds whatever the model produces.
Stack
- Engine: Python 3.8+ stdlib (
v3/kernel.py,v3/bayesian.py,v3/diagnostics.py,v3/calibration.py) - Web server: Python stdlib
http.server(v3/server.py, port 8420) - UI: Single-page vanilla HTML/JS/CSS (
v3/static/index.html) — no React, no framework, no build step - Native acceleration (optional): Rust crates at
crates/simengine-coreandcrates/simengine-py(PyO3), built with maturin - Tests: Python
unittestatv3/tests/ - MCP server:
v3/mcp_server.py(config:v3/mcp_config.json) - Natural-language front door (optional):
v3/llm/+ thev3/sim_ask.pyCLI + the/api/askendpoint + the web "Ask anything" tab. Local-first via Ollama; OpenAI/Anthropic via env var.
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 · 125 lines · 2,254 tokens per session scan A 67a50e3fd8ff
simengine CLAUDE.md is an instructions file published in the GitHub repository cogswellspacely8-star/simengine (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,254 tokens to every session, about $0.0113 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.