Running Claude Code in a loop to mirror human development practices

kept by eddie dec 12, 25

A continuous loop running Claude Code with persistent context and GitHub CI validation iteratively improves a large codebase's test coverage.

Show HN: Continuous Claude – run Claude Code in a loop
Continuous Claude runs Claude Code in a loop, autonomously creating PRs, waiting for checks, and merging, enabling multi-step projects to complete while the user sleeps.
also on Don Syme, Continuous Claude, GitHub, #cli, Claude Code, #ai-coding, #software-engineering, #developer-tools
GitHub - parcadei/Continuous-Claude-v2: Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
Continuous Claude is a framework that extends Claude Code with hooks, agents, and a 5-layer code analysis system to maintain session context, reduce token usage, and enable multi-agent development workflows.
also on Continuous Claude, #cli, Claude Code, #ai-coding, #software-engineering, #developer-tools
Don't rely on instructions, use Agent Hooks to enforce guardrails – Zarar's blog
Agent hooks (PreToolUse and Stop) enforce coding rules deterministically, preventing raw HTML tags and blocking task completion until a design-system test passes.
also on #testing, #cli, Claude Code, #ai-coding, #software-engineering, #developer-tools
Compound Engineering - The Next Paradigm Shift in Software Engieering
Compound engineering uses AI agents, automated testing, and rapid feedback loops to achieve 300-700% productivity gains by treating each completed task as an investment that accelerates future development. The feedback loop becomes the critical bottleneck when code generation speed approaches near-instant.
also on #testing, Claude Code, #ai-coding, #software-engineering, #developer-tools