Question 1

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

Accepted Answer

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.

Question 2

What do I need to run it?

Accepted Answer

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.

Question 3

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

Accepted Answer

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.

Question 4

Are Claude Code skills safe to install?

Accepted Answer

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.

Question 5

Does SecureContext send my code or data to the cloud?

Accepted Answer

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.

Question 6

Can it manage a long, multi‑week project?

Accepted Answer

Yes — that's what the delivery layer is for. Define a program with phases (zc_program), and the open phase's acceptance checklist travels with the project state. Closing a phase requires an evidence table and generates a checkpoint document automatically. If the orchestrating agent dies mid‑phase, a fresh one reconstructs the full delivery state from two calls — verified live.

Question 7

How much does SecureContext reduce Claude Code token costs?

Accepted Answer

Measured across a 10-session project: about 87% less context‑overhead (session restore is ~1.5–4k tokens instead of 20–50k of re‑pasted files). On long‑lived projects with hundreds of accumulated memories, the recall budget keeps each recall at ~4k tokens where an unbounded dump would be ~47k. File questions are answered from 15–50× compressed semantic summaries instead of raw reads.

Question 8

How do I give Claude Code persistent memory across sessions?

Accepted Answer

Install SecureContext (one command — see Quick start), then agents call zcremember to persist decisions and gotchas and zcrecall_context({focus: "current task"}) at session start to restore them — ranked by relevance, with natural-language time queries answered directly from memory. Memory survives restarts, compactions, and reboots because it lives in PostgreSQL, not in the context window.

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

Overview

Key features

Pricing

Use cases

Developer Onboarding

Code Review Process Improvement

Pros & Cons

Pros

Cons

Reviews

Q&A

Ask a question

Skills alternatives