← ClaudeAtlas

claude-code-frameworklisted

Authoritative reference for how Claude Code itself works AND how to build for it — CLAUDE.md memory, custom slash commands, subagents, skills, hooks, MCP servers, settings precedence, permissions, plan mode, CLI/headless/CI, worktrees, and multi-platform surfaces. Use when authoring or debugging a plugin component (command/agent/skill/hook), wiring an MCP server, choosing frontmatter fields, configuring settings.json or permissions, figuring out why an agent/skill won't auto-trigger, running headless/CI or worktree-parallel sessions, or answering "how does Claude Code X work / how should I structure this for Claude Code."
nxtg-ai/forge-plugin · ★ 5 · AI & Automation · score 76
Install: claude install-skill nxtg-ai/forge-plugin
# Claude Code Framework — Reference & Decision Guide Authoritative reference for Claude Code's behavior and for authoring its extensions. Ground every claim to current behavior at <https://code.claude.com/docs>. Model IDs, pricing, and "as of version X" specifics rot — re-verify against live docs before relying on them. This file is the index; depth lives in the linked reference files. --- ## CORE OPERATING RULES Apply these directly when working *with* Claude Code on real tasks: 1. **Plan before code on anything non-trivial.** Use Plan Mode (or a written plan) to agree on approach before edits. Discussion-then-code catches wrong turns cheaply. 2. **Keep CLAUDE.md lean and failure-focused.** Document what Claude gets *wrong* in this repo (build quirks, forbidden paths, naming rules), not what it does right. ~100–200 lines; past ~40k chars Claude Code warns performance degrades — move depth into skills/docs and link them. 3. **Clear context aggressively.** `/clear` between unrelated tasks; provide only files relevant to the current task. Don't let one session accumulate stale context. 4. **TDD as guardrail.** Write/keep failing tests first, let Claude iterate to green. Tests are the objective signal that beats "looks done." 5. **Split write vs. review contexts.** Have a fresh context or subagent verify code the first context wrote — a single context rationalizes its own mistakes. 6. **Checkpoints ≠ version control.** `/rewind` (or double-Esc) restores