What is datarobot-agent-assist-simulate?

An adversarial testing process for an implemented AI agent before deployment. It runs attack, behavior, and persistence simulations to find ways the agent can fail or be manipulated.

Use it to simulate attacks, check whether the agent follows expected behavior, test resistance to repeated or persistent manipulation, patch failures, and produce an evaluation report.

It exposes weaknesses before users encounter them and retests fixes across multiple rounds. The process continues until the scenarios pass or the configured fixing limit is reached.

datarobot-agent-assist-simulate — Skill for Claude Code by datarobot-o

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.

Any agent

npx skills add datarobot-oss/datarobot-agent-skills --skill agent-assist-simulate

Clone the repo

git clone --depth 1 https://github.com/datarobot-oss/datarobot-agent-skills

Made for: Claude Code.

Or install datarobot-agent-skills, the plugin that ships this one along with the rest of its 17 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/datarobot-oss/datarobot-agent-skills/agent-assist-simulate/github.svg)](https://agentmods.dev/skills/datarobot-oss/datarobot-agent-skills/agent-assist-simulate)

Your own site

<a href="https://agentmods.dev/skills/datarobot-oss/datarobot-agent-skills/agent-assist-simulate"><img src="https://agentmods.dev/badge/skills/datarobot-oss/datarobot-agent-skills/agent-assist-simulate/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/datarobot-oss/datarobot-agent-skills/agent-assist-simulate"><img src="https://agentmods.dev/badge/skills/datarobot-oss/datarobot-agent-skills/agent-assist-simulate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,377 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00051	$0.04377
Opus 5	$0.00026	$0.02188
Sonnet 5	$0.00010	$0.00875
Haiku 4.5	$0.00005	$0.00438

Measured 11d ago against content hash 608d094b9454, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

datarobot-agent-assist-simulate scanned grade C with 2 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 11d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (scripts/artifacts.py, scripts/gateway_worker.py, scripts/native_convergence.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

session that did not complete Step 5 cleanup. Run `rm -rf .datarobot/swarm/` before proceeding.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

until curl -sf http://127.0.0.1:4096/global/health >/dev/null 2>&1; do sleep 0.25; done

skills/datarobot-agent-assist/agent-assist-simulate/SKILL.md · 445 lines

How it starts

The opening of the file, as written. The whole thing — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Assist — Simulate

Adversarially test and harden an implemented agent before deployment. Runs three simulation tracks (attack, behavior, persistence), then patches and retests failing scenarios across multiple rounds until all pass or the fixing limit is reached.

Script Path Resolution

Resolve once per session: <skill_scripts_dir> is the scripts/ subdirectory next to this SKILL.md. Confirm it exists. Use the resolved absolute path everywhere.

Python: prefer .venv/bin/python3 if a .venv/ exists; otherwise python3. Store as <python>. Require 3.11+:

<python> -c "import sys; assert sys.version_info >= (3, 11)"
<python> -c "import pydantic, yaml" 2>/dev/null || <python> -m pip install pydantic pyyaml

OpenCode:

dr opencode upgrade && export PATH="$PATH:$HOME/.opencode/bin"

Auth:

dr auth check
dr dotenv update

If any check fails, surface the error and stop.

Swarm directory: All intermediate files (scenario inputs/outputs, run results, convergence state) are written to .datarobot/swarm/ under the project root and deleted at the end of Step 5.

If .datarobot/swarm/ already exists at the start of a session, it is leftover from a prior session that did not complete Step 5 cleanup. Run rm -rf .datarobot/swarm/ before proceeding.

Pre-flight Check

Confirm agent_spec.md exists with a system_prompt. If not, route the user to agent-assist-build and stop.
Confirm implementation code exists (agent.py, myagent.py, tools.py, or app.py). If not, route to agent-assist-build and stop.

Step 1 — Configure

Collect answers in sequence. Do not start simulation until all are answered.

If agent_config.yaml already exists, read it and ask:

"Last time: [persona], [context or none], [iterations] rounds of fixing, [eval mode], [model]. Same settings or change anything?"

Q1 — User type: Read agent_spec.md and offer 2–4 domain-specific personas plus "Other — describe your user segment."

Read the full file on GitHub · 445 lines

Files

What ships with it

17 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.

11d ago First seen · 445 lines · 51 tokens per session scan C 608d094b9454

Subscribe to this mod's changes

datarobot-agent-assist-simulate is a skill published in the GitHub repository datarobot-oss/datarobot-agent-skills (25 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 4,377 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents Testing claude-skills cursor-plugins gemini-cli-extension skills

offensive-fuzzing

Practical offensive fuzzing methodology covering target identification, fuzzer selection (AFL++, libFuzzer, Honggfuzz, Boofuzz, syzkaller), harness writing, corpus curation, mutation strategies, coverage measurement, and crash triage. Use when setting up or running fuzz campaigns against any target: file parsers…

SnailSploit/Claude-Red · 91 tokens

offensive-business-logic

Business logic vulnerability testing for web/mobile/API engagements. Covers workflow bypass, state machine violations, multi-step process abuse, price/quantity/discount manipulation, currency confusion, coupon stacking, refund/chargeback abuse, race conditions on logic boundaries, parameter tampering for hidden flows…

SnailSploit/Claude-Red · 135 tokens

offensive-race-condition

Race condition (TOCTOU) testing checklist: identifying timing windows, Burp Suite Turbo Intruder, Last-Byte sync technique, rate limit bypass, double-spend attacks, and concurrent request exploitation. Use for web app race condition testing or bug bounty time-of-check-to-time-of-use bugs.

SnailSploit/Claude-Red · 0 tokens

smoke-test

Launch the app and hands-on verify that it works by interacting with it. Falls back to an existing integration test suite when there is no interactive surface in scope. Use when the user asks to "smoke test", "test it manually", "verify it works", "try it out", "run a smoke test", "check it in the browser", or "does…

tobihagemann/turbo · 88 tokens

exploratory-test

Execute multi-level exploratory testing of the app covering basic functionality, complex operations, adversarial testing, and cross-cutting scenarios, plus usability observations through a UX lens reported separately from defects. Deeper than /smoke-test. Use when the user asks to "exploratory test", "test…

tobihagemann/turbo · 106 tokens

create-test-plan

Analyze what changed and generate a structured test plan at .turbo/test-plans/ .md covering four escalating levels: basic functionality, complex operations, adversarial testing, and cross-cutting scenarios. Use when the user asks to "create a test plan", "plan tests", "what should I test", "generate test scenarios"…

tobihagemann/turbo · 87 tokens

datarobot-agent-assist-simulate