SteelMorgan

When writing or reviewing BSL, apply 1C standards

При написании или ревью BSL применять стандарты 1С

Orchestrator: routing work and agent phases

Оркестратор: маршрутизация работы и фаз агентов

BSL LSP navigation: definitions, refs, call graph

Rules for using RLM tools for project search and navigation in 1C/BSL

Find an existing equivalent before new BSL code

LSP-навигация BSL: definitions, refs, call graph

Standardizes git workflow for the AI agent in the sandbox devcontainer: work in agent/<task>-<yyyymmdd>, integrate via agent, never push to main/master, open PRs via GitHub CLI. Use when the user asks to create branches, push changes, open PRs, or follow this sandbox repo setup.

Behavior + permission model for the AI agent inside the sandbox devcontainer. The agent has sudo and may modify its container environment freely to solve tasks, but must never bypass explicit safety restrictions (git hooks/blocks, policy rules) or escalate beyond the sandbox.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Define, review, and apply the `learn` and `enforce` network modes for the MAX isolation project. Use when working on guest firewall rules, allowlists, connection logging, network classification, flow verification, or any change that affects what MAX may reach over the network.