simulate

A simulated participant that knows no task: a pool that answers each trial with one of the options it lists, at random, seeded by the run.

Skill by behaverse

IndexedMIT

Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/behaverse-simulate

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

A simulated participant that knows no task: a pool that answers each trial with one of the options it lists, at random, seeded by the run. Use to run a study on this machine before any person or model takes it, where what the answers are does not matter.

Use cases: productivity

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found
Runs as: Python package

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/simulate

What's inside

Skill name: simulate
Description: A simulated participant that knows no task: a pool that answers each trial with one of the options it lists, at random, seeded by the run. Use to run a study on this machine before any person or model takes it, where what the answers are does not matter.
License: MIT
Compatibility: Local runtime with uv; standard library only.
Metadata: schemes: simulate
Instructions: 13 lines in SKILL.md · view on GitHub

Before installing

Ships executable scripts

Files (3)

SKILL.md
local.py
test_local.py

SKILL.md (first lines)

A runner-only skill. It claims every pool with no process whose `studyflow:Actor` `implementation` is
`simulate://random`, and answers each message sent to it with one of the options the message lists
(`ResponseOptions`, at the message's top level or in the one value of it that lists some), drawn by the study's seed
and the message's id, so a run repeats exactly. A message that lists no options is an instruction, which it confirms
with `READY`.

It knows no task, so it plants no effect, and it never fails to answer. A study that needs answers whose truth it knows,
to check that its analysis recovers an effect, draws a simulated actor of its tasks' own skill instead (for the
Behaverse battery, a pool typed `behaverse:SimulatedActor`, its planted accuracies written in the study). Swap the pool's
`implementation` for `ollama://<model>` and the same file asks a language model instead. `test_local.py` is its
self-check.

From behaverse/studyflow-modeler, MIT.

Signals

Stars: 0
Forks: 0
Open issues: 15
Last commit (this folder): Oct 12, 2026 (17 days ago)
Last release: Oct 22, 2026 (6 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/behaverse/studyflow-modeler
Website: behaverse.org/studyflow-modeler/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from behaverse

Cite this page

simulate skill. Agent Mart. https://agentmart.dev/skills/behaverse-simulate (last updated 2026-10-24)