developer-git-workflow (Grade A)Security-tested data-ai skill for Claude AI. Grade A. GIT WORKFLOW — extracted from roles.json deepPrompt for developer

Which local models should I run, and how does hardware affect SecureContext?

SecureContext degrades gracefully by hardware tier — every LLM‑powered layer fails closed (the feature quietly contributes nothing) rather than breaking ingest or search. Minimum tier (any CPU, ~2 GB RAM) runs nomic‑embed‑text for embeddings and provides hybrid BM25+vector search, working memory, audit chain, and skills gating. Mid tier (8–16 GB GPU or Apple Silicon 16 GB+) adds a 14‑billion‑parameter model (qwen2.5‑coder or phi4) for event extraction, entity extraction, and semantic summaries. Full tier (24 GB+ GPU) runs both phi4 and gpt‑oss models concurrently, delivering the complete feature set at interactive latency.

Asked by Yuki Kobayashi · Mar 2, 2026

What do I need to run it?

Node 20+ and (recommended) Docker for the bundled PostgreSQL + Ollama stack. The one‑command installer does everything in about five minutes. A SQLite fallback runs with zero infrastructure.

Asked by Carmela Esposito · Feb 15, 2026

Can multiple Claude Code sessions work on the same project without conflicts?

Yes — parallel sessions atomically claim tasks from a work‑stealing queue (zero double‑claims at 50 agents × 100 tasks in testing), coordinate through typed broadcasts (ASSIGN/STATUS/MERGE/REJECT), and keep private per‑agent memory namespaces plus a shared pool. Department‑style hierarchies (heads + workers, N‑tier escalation) are supported for larger agent teams.

Asked by Henrik Dahl · Feb 9, 2026

Are Claude Code skills safe to install?

Filesystem skills bundle scripts that run with your permissions, and Claude Code's native loader does not scan them. SecureContext adds the missing gate: AST scan at admission, HMAC verification before every execution, automatic quarantine on failure or post‑admission change, and a verifiable chained log of every admission decision.

Asked by Celeste Marchetti · Feb 5, 2026

Does SecureContext send my code or data to the cloud?

No. Memory, embeddings (Ollama nomic‑embed‑text), search, summarization, and the audit chain all run locally. It works fully offline (search degrades gracefully to keyword‑only if Ollama is down) and costs $0 when idle.

Asked by Paulo Cardoso · Dec 22, 2025