pilot-shell - production gates for Claude Code

TypeScript harness that wraps Claude Code with spec-driven plans, enforced quality gates, and persistent project knowledge. Targets teams shipping production code with the agent rather than prototyping.

Saved Apr 28, 2026View source ↗

#claude-code #typescript #ai-agent #orchestration

This entry doesn't have a long-form writeup yet. Follow the source link above for the full context.

Recent discussion

From the wider web

Featured in

Claude Code tools, plugins, and integrations
The best tools, MCP servers, and harnesses for getting more out of Claude Code - orchestration, observability, telemetry, and remote control.

Related entries

GitHub ToolFeatured

wanman - worktree-isolated multi-agent runtime for Claude Code and Codex

Multi-agent runtime that spawns each Claude Code or Codex agent in its own git worktree and home directory. JSON-RPC subprocess control, task pooling, artifact storage. Solves the share-a-directory failure mode that breaks most multi-agent harnesses.

Why I saved this - The 'one-man train' framing is load-bearing: humans observe rather than approve every step. Worktree-per-agent isolation is the upgrade most multi-agent harnesses skip.

#claude-code #codex #multi-agent #orchestration #typescript

GitHub ToolFeatured

trace-mcp - framework-aware codebase MCP for coding agents

MCP server with 138 tools and cross-language framework awareness (58 integrations across 81 languages). Indexes Laravel/Inertia/Vue, Rails/Hotwire, Django/HTMX edges so agents skip re-deriving call graphs. Decision memory links architectural choices to the code they're about. Local-first ONNX embeddings, optional LSP enrichment.

Why I saved this - Distinct from Qartez - Qartez is structural (PageRank, blast radius), trace-mcp is framework-semantic. The cross-language edges (Laravel controller -> Vue page via Inertia) are the differentiated bit.

#mcp #claude-code #code-intelligence #typescript #static-analysis

GitHub ToolFeatured

Claudraband - persistent, resumable Claude Code sessions over HTTP and ACP

Wraps the real Claude Code TUI with a session lifecycle layer. Resumable non-interactive workflows, HTTP daemon for remote/headless control, ACP server for editor integrations (Zed, Toad). Drives your existing Claude Code install rather than reimplementing it - keeps skills, hooks, MCPs, and approvals intact.

Why I saved this - Different from the Claude SDK - Claudraband drives the real CLI from outside, so user-installed skills/hooks/MCPs all still work. The ACP support is the easy path to editor integrations.

#claude-code #remote-control #developer-tools #typescript #cli

GitHub ToolFeatured

pentest-ai-agents - Claude Code subagents for offensive security

Specialized Claude Code subagents that turn the CLI into a pentest assistant: plan engagements, analyze recon, research exploits, build detections, audit STIGs, and write reports.

Why I saved this - Authorized-use scope is explicit in the README - it is a research harness, not a 'jailbreak the agent' kit.

#claude-code #security #pentest #ctf #ai-agent