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 skills/synaptiai/agent-capability-standard/simulatenpx skills add synaptiai/agent-capability-standard --skill simulategit clone --depth 1 https://github.com/synaptiai/agent-capability-standardWhat 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 | $0.00034 | $0.02366 |
| Opus 5 | $0.00017 | $0.01183 |
| Sonnet 5 | $0.00007 | $0.00473 |
| Haiku 4.5 | $0.00003 | $0.00237 |
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.
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
-
Set up scenario: Define what is being simulated
- Clarify the intervention or change being tested
- Establish initial conditions
- Define simulation boundaries
-
Initialize state: Establish starting point
- Use provided initial_state or current system state
- Validate state is consistent
- Note any simplifications
-
Execute simulation: Step through scenario
- Apply changes specified in scenario
- Propagate effects through state
- Track state at each step
-
Explore branches: Consider alternative paths
- Identify decision points
- Explore likely alternative outcomes
- Note probability of each branch
-
Evaluate outcomes: Assess simulation results
- Compare final states across branches
- Identify risks and opportunities
- Note unexpected behaviors
-
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"]
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.
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 · 334 lines · 34 tokens per session scan A d0eca9a29f20
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.
Other skills, from other repositories
employment-contract-templates
Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment documentation.
rag-implementation
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.
hugging-face-dataset-creator
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, and streaming row updates. Designed to work alongside HF MCP server for comprehensive dataset workflows.
prompt-engineering-patterns
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.
calendar-event-create
Create a Google Calendar event with title, time, and attendees.
file-read
Read a file from an allowed path on the local filesystem.