designer-common-anti-patterns (Grade A)セキュリティテスト済みのデータ_AIスキルです。クラウドAIに適合。 Grade A. COMMON ANTI-PATTERNS — extracted from roles.json deepPrompt for designer

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. What changes with hardware is how much of the intelligence stack is active: | Tier | Hardware | Models that fit | What you get | |---|---|---|---| | Minimum | Any CPU, ~2 GB RAM free | nomic-embed-text (embeddings only) | Hybrid BM25+vector search, working memory, audit chain, skills gating — the core. LLM layers (event extraction, entity extraction, contradiction adjudication) stay dormant. | | Mid | 8–16 GB GPU (or Apple Silicon 16 GB+) | + qwen2.5-coder:14b or phi4:14b (one at a time) | + Event-fact extraction at ingest (temporal reasoning), LLM contradiction adjudication, entity extraction, L0/L1 semantic file summaries. | | Full | 24 GB+ GPU (e.g. RTX 4090/5090) | + phi4:14b and gpt-oss:20b resident together | Everything, concurrently, at interactive latency — plus a strong local generator for QA/benchmarks. This is the configuration our published benchmark deltas were measured on. | Model-choice guidance (all measured, see bench/): Embeddings: nomic-embed-text — required, tiny, runs anywhere. Event extraction (ZCEVENTEXTRACTMODEL, default phi4:14b): our bakeoff scored phi4:14b at 100% event recall / 100% date accuracy, tying gpt-oss:20b at 2× the speed. On smaller GPUs qwen2.5-coder:14b is close behind (84.6% recall). Coder models ≠ better: qwen2.5-coder:32b scored worst (69.2%) despite being the large

Asked by Vera Nováková · Aug 29, 2025

動かすには何が必要ですか？

Node 20+ と（推奨）Docker が必要です。バンドルされた PostgreSQL + Ollama スタックを使用します。ワンコマンドインストーラで約5分でセットアップ完了。SQLite フォールバックはインフラ不要で動作します。

Asked by Elena Rossi · Aug 20, 2025

複数のClaude Codeセッションは、衝突なく同じプロジェクトで作業できますか？

はい。パラレルセッションは、ワーク・スティーミングキューからタスクを原子的に取得します（テストで50エージェント×100タスクの際、二重取得ゼロ）。ASSIGN/STATUS/MERGE/REJECT の型付きブロードキャストを介して調整し、各エージェントのプライベートメモリ名前空間と共有プールを保持します。大規模エージェントチーム向けには、ヘッド＋ワーカー、N階層エスカレーションといった部署形式の階層構造もサポートしています。

Asked by Dara Fitzgerald · Aug 13, 2025

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 Rasheed Osman · Aug 10, 2025

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 Mei-Ling Wong · Jul 26, 2025