id-simulate

id-simulate is a skill for Claude Code, Codex from lukasrepublic/agentic-foundry. It costs 370 tokens per session (3,707 once invoked), scanned A, original, MIT.

An offline procedure for simulating infrastructure changes locally, without cloud access or credentials, before checking them against the live environment.

In plain words
What is it for?
Use it to run infrastructure modules and GitOps structures against local simulators before the live planning step.
Why use it?
It tests more than formatting and policy checks can show, while avoiding changes to real infrastructure.

Skill for Claude CodeCodex

Part of the foundry plugin — 47 skills, 8 agents, 8 hooks, 1 MCP server shipped together

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 skills/lukasrepublic/agentic-foundry/id-simulate
Any agent
npx skills add lukasrepublic/agentic-foundry --skill id-simulate
Clone the repo
git clone --depth 1 https://github.com/lukasrepublic/agentic-foundry

Made for: Claude Code, Codex.

Or install foundry, the plugin that ships this one along with the rest of its 47 skills, 8 agents, 8 hooks, 1 MCP server.

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.

agentmods badge for id-simulate

README.md
[![agentmods](https://agentmods.dev/badge/skills/lukasrepublic/agentic-foundry/id-simulate.svg)](https://agentmods.dev/skills/lukasrepublic/agentic-foundry/id-simulate)
Your own site
<a href="https://agentmods.dev/skills/lukasrepublic/agentic-foundry/id-simulate"><img src="https://agentmods.dev/badge/skills/lukasrepublic/agentic-foundry/id-simulate.svg" alt="Measured on agentmods" height="20"></a>
Per session 370 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,707 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00370 $0.03707
Opus 5 $0.00185 $0.01853
Sonnet 5 $0.00074 $0.00741
Haiku 4.5 $0.00037 $0.00371

Measured 3d ago against content hash 46e4f95a803a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

id-simulate 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 3d 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.

skills/id-simulate/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

id-simulate — OFFLINE local-simulation craft (infra-delivery step, between id-test and id-plan)

The infra-delivery step sequence (a documented procedure this skill family forms — no workflow engine or state-machine file ships) drives an infra change → merge. The simulate step runs after id-test (the Layer-0 policy/contract test) and before id-plan (the read-only pre-merge plan/diff seam). It is the offline local-simulation layer: a PROCEDURE skill the generic agent runs entirely offline — with no live cloud and no credentials — to author-and-prove the whole IaC corpus before the live pre-merge plan.

The Layer-0 steps (id-validate fmt/lint/render + id-test policy/contract tests) prove the change validates and renders / policy-passes; they cannot prove the primitive modules apply or that the GitOps structure reconciles. id-simulate closes that gap with the two offline layers — short of live cloud, the highest-value signal an adopter can get — by driving the profile's existing IaC against local simulators. It needs no new infra_binding slot (it drives the profile's already-named modules + gitops_paths tree offline).

OFFLINE — no live cloud, no credentials (the load-bearing safety invariant)

This step is OFFLINE. Every Layer-1 apply is against the LocalStack endpoint (--endpoint-url / a tflocal provider override + a backend "local" state) — it applys the primitive modules to a simulator, never a real AWS account, and it is not the profile's infra_binding.apply live-mutation slot. Every Layer-2 apply/reconcile is against a throwaway local kind/k3d cluster — never the guarded live cluster. Because everything is local-only, this step runs entirely offline: no live cloud account, no live cluster, no credentials, and it issues no mutating command against either. (Layer 2 does stand up a throwaway local kind/k3d cluster — that is the local simulator itself, never a live cluster or credentials of any kind.) It is the offline complement to the read-only id-validate/id-test: those never mutate anything; id-simulate mutates only local simulators, never live state.

Read the full file on GitHub · 159 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. 3d ago First seen · 159 lines · 370 tokens per session scan A 46e4f95a803a

Subscribe to this mod's changes

id-simulate is a skill published in the GitHub repository lukasrepublic/agentic-foundry (1 stars, last pushed 2d ago), licensed MIT. It adds 370 tokens to every session and 3,707 once invoked, about $0.0019 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 2026-08-31.