simulate

A what-if analysis capability that steps through a proposed change, event, or intervention without making real changes. It can examine one path, branching paths, or exhaustive possibilities from a stated starting point.

In plain words
What is it for?
Use it to stress-test designs, compare alternatives, explore scenarios, and examine how a system might behave after a change.
Why use it?
It lets you explore likely outcomes and edge cases before acting on a real system. It also makes assumptions and important decision points explicit.

Skill for Claude CodeCodex

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/synaptiai/agent-capability-standard/simulate
Any agent
npx skills add synaptiai/agent-capability-standard --skill simulate
Clone the repo
git clone --depth 1 https://github.com/synaptiai/agent-capability-standard

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,366 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 $0.00034 $0.02366
Opus 5 $0.00017 $0.01183
Sonnet 5 $0.00007 $0.00473
Haiku 4.5 $0.00003 $0.00237

Measured 2d ago against content hash d0eca9a29f20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

skills/simulate/SKILL.md · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Intent

Execute mental simulations of scenarios to explore outcomes without making real changes. This capability enables safe exploration of "what-if" questions and helps identify risks before action.

Success criteria:

  • Scenario executed through logical steps
  • Multiple outcomes considered
  • Key decision points identified
  • Assumptions made explicit

Compatible schemas:

  • schemas/output_schema.yaml

Inputs

Parameter Required Type Description
scenario Yes object Scenario to simulate (intervention, change, event)
initial_state No object Starting state for simulation
steps No integer Number of simulation steps/iterations
explore No string What to explore: single_path, branches, exhaustive

Procedure

  1. Set up scenario: Define what is being simulated

    • Clarify the intervention or change being tested
    • Establish initial conditions
    • Define simulation boundaries
  2. Initialize state: Establish starting point

    • Use provided initial_state or current system state
    • Validate state is consistent
    • Note any simplifications
  3. Execute simulation: Step through scenario

    • Apply changes specified in scenario
    • Propagate effects through state
    • Track state at each step
  4. Explore branches: Consider alternative paths

    • Identify decision points
    • Explore likely alternative outcomes
    • Note probability of each branch
  5. Evaluate outcomes: Assess simulation results

    • Compare final states across branches
    • Identify risks and opportunities
    • Note unexpected behaviors
  6. Document simulation: Record process and results

    • List assumptions made
    • Note limitations of simulation
    • Provide evidence for conclusions

Output Contract

Return a structured object:

outcomes:
  - branch_id: string  # Unique branch identifier
    probability: number  # Estimated likelihood
    final_state: object  # State after simulation
    key_events: array[string]  # Notable events during simulation
    risks: array[string]  # Identified risks
trajectory:
  - step: number
    state: object  # State at this step
    changes: array[string]  # What changed
final_state: object  # Most likely final state
insights:
  - type: string  # risk, opportunity, surprise
    description: string
    severity: string  # low, medium, high
simulation_meta:
  steps_executed: number
  branches_explored: number
  assumptions: array[string]
confidence: 0..1
evidence_anchors: ["model:component", "assumption:id"]

Read the full file on GitHub · 334 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 334 lines · 34 tokens per session scan A d0eca9a29f20

Subscribe to this mod's changes

simulate is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 34 tokens to every session and 2,366 once invoked, about $0.0002 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.