settings.json layering: file locations, precedence, and permissions merging

AGENTS.md compatibility (cross-agent shared instructions)

CLAUDE.md rule drift in long sessions (and when to use hooks instead)

Output styles: format, scope, and interaction with CLAUDE.md / system prompt

Adding an MCP server: transports, scopes, and the claude mcp add command

MCP server shows Connected but exposes 0 tools

Custom model endpoints and gateway routing

Custom slash command argument handling and frontend stripping bugs

CLAUDE.md rule drift in long sessions (and when to use hooks instead)

PreToolUse:Bash hooks silently not firing (v2.1.176+ regression)

Context window overflow and /compact failure modes

API 400 'tool_use without tool_result' and parallel-tool conversation corruption

Authenticating claude-code-action: API key vs Max/Pro subscription

OIDC / token-exchange failures and bot-triggered workflow 401s

CI install hangs and SDK crashes in claude-code-action

CI permissions syntax: 'Bash' vs 'Bash(*)' and the sticky-review comment

Context window overflow and /compact failure modes

Subagent recursive self-spawn and orchestration explosions

Session vs weekly quotas: why usage feels wrong

Token-spend levers: the cost-control playbook

Windows native binary stability and crash recovery

Image paste in WSL2 / Windows Terminal: Ctrl+V unreliable, use drag-drop or file paths

Windows nul device file artifacts: creation, deletion, and prevention

Windows shell selection via shellPath: Git Bash auto-detection causing find/ls/grep hangs

JetBrains plugin IDE integration failure in WSL: WSLENV variable passthrough

Image paste in WSL2 / Windows Terminal: Ctrl+V unreliable, use drag-drop or file paths

Output styles: format, scope, and interaction with CLAUDE.md / system prompt

VS Code extension session persistence across folder switches

Model quality regression: official postmortem on context-routing, output corruption, and token-selection bugs

Pro/Max credentials via third-party CLI: policy, abuse classifier risks, and when to use API key instead

Account Registration & SMS Verification Failures

Organization Disabled: API key conflict vs account suspension

Session initialization and lifecycle: explore → plan → verify → iterate

Configuration layering: CLAUDE.md vs CLAUDE.local.md vs skills vs subagents

Subagent definition schema and scope resolution

Hatch / Hidden venv discovery and per-invocation environment setup

Multi-agent orchestrator tool types and selection matrix