simulator-ai-plugin AGENTS.md

Repository guidance for coding agents working on a Simulator.Company plugin. It explains the project’s purpose, folder layout, commands, conventions, and common mistakes.

In plain words
What is it for?
Use it when modifying the plugin, its Go MCP server, or its 14 skills. It also points to the architecture and usage documents that explain how the system works.
Why use it?
It gives an agent the project context needed to make changes in the right places and follow the repository’s rules.

Instructions file for CodexOpenCode

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/corezoid/simulator-ai-plugin/agents-md
Clone the repo
git clone --depth 1 https://github.com/corezoid/simulator-ai-plugin

Made for: Codex, OpenCode.

Per session 3,082 This file is loaded in full into every session.
When invoked 3,082 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 $0.03082 $0.03082
Opus 5 $0.01541 $0.01541
Sonnet 5 $0.00616 $0.00616
Haiku 4.5 $0.00308 $0.00308

Measured 2d ago against content hash 5dffc5c650ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simulator-ai-plugin 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 · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for coding agents (Codex, Claude Code, etc.) working in the simulator-ai-plugin repository. Humans: see the root README.md (usage) and docs/ARCHITECTURE.md (design).

What this repo is

A plugin for Claude Code, Codex, and AWS Kiro that connects the Simulator.Company platform (backend: pong-server / control-api) to the host via MCP. It bundles:

  • a Go MCP server (plugins/simulator/mcp-server/) that exposes the Simulator /papi/1.0 public API as a curated, typed set of ~95 MCP tools (declared in Go, not a generic spec passthrough), scoped to the core scenarios;
  • 14 skills (plugins/simulator/skills/) — markdown that teaches the model the platform's entity model and common workflows.

Read docs/ARCHITECTURE.md before making non-trivial changes.

Layout (the parts you'll touch)

plugins/simulator/mcp-server/   Go MCP server (Go 1.24+, mark3labs/mcp-go)
  cmd/server/                   entry point: profile → apiclient → tools → stdio
  cmd/gendiscovery/             regenerate public/ discovery artifacts
  cmd/evalrunner/               behavioural eval (opt-in; needs ANTHROPIC_API_KEY)
  internal/config/              cloud presets + local/prod profiles (env + profiles.json overridable)
  internal/apiclient/           HTTP client: base URL, auth header, accId, timeouts, errors
  internal/tools/               curated typed Operation registry (op.go) + per-domain files
    testdata/                   papi-openapi.json (drift gate) + eval-scenarios.json
  internal/engines/             graph sync, layout, prune, placements, upload, chart
  app/auth/                     set-environment (public config → account URL) + OAuth2 PKCE + .env credential storage
plugins/simulator/skills/       14 skills (markdown only, ship with the plugin)
plugins/simulator/docs/         entity & user-flow reference (ships with the plugin)
docs/                           contributor docs (ARCHITECTURE.md, INTEGRATION.md) — repo-level
public/                         generated AI-discovery artifacts (do not hand-edit)

Read the full file on GitHub · 187 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. 2d ago First seen · 187 lines · 3,082 tokens per session scan A 5dffc5c650ce

Subscribe to this mod's changes

simulator-ai-plugin AGENTS.md is an instructions file published in the GitHub repository corezoid/simulator-ai-plugin (60 stars, last pushed 5d ago), licensed MIT. It adds 3,082 tokens to every session, about $0.0154 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.