antonbabenko

When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.

System design, tradeoffs, and complex technical decisions.

Rank root-cause hypotheses and propose the smallest safe fix.

Validate that a work plan is executable before work starts.

Catch ambiguities and hidden requirements before planning.

Find bugs, security holes, and maintainability issues in a diff or file.

Research external libraries, APIs, and best practices, with evidence.

Threat-model and find vulnerabilities, with practical remediation.

Guidelines for adding new agent skills: always register in AGENTS.md, and prefer deterministic scripts with unit tests over pure SKILL.md for repeatable workflows.

How to create commits, GitHub issues, and PRs for this repo: Conventional Commits with AI attribution, repo issue/PR templates, draft PRs with What/Why/Assisted-by sections.

Use when writing, reviewing, or debugging Terraform/OpenTofu modules, tests, CI, scans, or state ops - diagnoses failure mode (identity churn, secrets, blast radius, CI drift, state corruption) with version-aware guards.

Use when navigating or refactoring code with a language server - choosing between semantic (LSP), exact-text (rg), and fuzzy/semantic search; anchoring LSP calls by position; gating degraded results; and disclosing tool substitutions, in any language.