Browse the directory

Community reusable agent prompt for recovering Claude Code sessions after auto-compaction or context thrashing using official context-window docs: rebuild goals from git, validate tasks, and block destructive edits after memory loss.

Context window optimization specialist managing 1M+ token conversations, preventing truncation with smart summarization and session management strategies.

Expert Claude Code context window audit capability pack for measuring what loads at session start, what each read and extension adds, when compaction drops path-scoped rules, and how to delegate or compact before quality drops.

Reduce Claude Code context pressure from MCP tools using MAX_MCP_OUTPUT_TOKENS, anthropic/maxResultSizeChars annotations, tool search deferral, alwaysLoad discipline, and pagination patterns from official MCP documentation.

Configure Claude Code statuslines for workflow visibility: model identity, context usage, git branch, session mode, and custom metrics so maintainers see agent state at a glance without leaving the terminal.

Configure Claude Agent SDK and Claude Code tool search so large MCP catalogs defer schemas until needed, using ENABLE_TOOL_SEARCH modes, alwaysLoad discipline, and context budgeting from official tool-search documentation.

A practical walkthrough of structuring CLAUDE.md across a monorepo: how files load up the directory tree and on demand in subdirectories, path-scoped rules, imports, excluding other teams' files, and keeping per-package context lean.

Source-backed agent that reduces token cost and latency in Claude Code by improving prompt-cache hit rates, advising on stable context ordering, lean CLAUDE.md, on-demand skills, and MCP tool-search, grounded in the official docs.

A practical walkthrough of the Claude Code context window: what consumes it (system prompt, memory, CLAUDE.md, MCP tools, skills, file reads, history), how each piece loads, and how the /context view helps you design leaner prompts and setups.

Fix Claude Code high CPU and memory usage, hangs, slow responses, and auto-compact thrashing using /context, /compact, /clear, /doctor, and documented context-management techniques.

MCP server for context-window optimization that routes large tool outputs through sandbox tools, indexes session state, and helps agents retrieve only the context they need.

A reusable agent prompt that vets a Claude Code plugin or marketplace before a team installs it. It walks source trust, the plugin's Will-install list and bundled components (skills, agents, hooks, MCP servers, commands), the context-window cost, version pinning, and the user/project/local/managed install scope.

Use the built-in /context command to inspect Claude Code's context-window usage, plus a custom .claude/commands recipe for repeatable codebase-context analysis before refactors.