h5i Guides

Practical guides for AI-era version control

Task-focused walkthroughs for using h5i with Claude Code and Codex — persistent memory and handoff, multi-agent coordination, AI code provenance, auditing AI-generated code, prompt-injection detection, and AI blame. Each guide: the problem, the h5i fix, the commands, a worked example, and an FAQ.

Guide · Memory & Handoff

Persistent memory & session handoff for Claude Code

Snapshot Claude Code's memory into Git, version your reasoning, and resume the next session from a briefing instead of re-grounding.

Guide · Multi-Agent

Claude Code + Codex: a multi-agent coding workflow

Let two coding agents coordinate over a Git ref — ask, review, hand off, and reply as durable, replayable messages with no server.

Guide · Provenance

AI code provenance: track AI-generated code in Git

Attach the prompt, model, agent, tokens, and test result to every AI-assisted commit — stored in Git, queryable like git log.

Guide · Audit & Review

Auditing AI-generated code: risk-rank what to review

Rank AI commits by uncertainty, blind edits, churn, and scope so reviewers spend their attention on the riskiest changes first.

Guide · Security

Detecting prompt injection in AI agent traces

Scan Claude Code reasoning traces for prompt-injection and exfiltration patterns — deterministic, with no model in the detection path.

Guide · Blame

git blame for AI-generated code

Per-line provenance for AI-written code: the prompt, the model, the agent, and the test result — same ergonomics as git blame.