datarobot-agent-assist-simulatelisted

# 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+: ```bash <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:** ```bash dr opencode upgrade && export PATH="$PATH:$HOME/.opencode/bin" ``` **Auth:** ```bash 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 1. Confirm `agent_spec.md` exists with a `system_prompt`. If not, route the user to `agent-assist-build` and stop. 2. Confirm implement