Plugin Claude Code
Plugin marketplace listing 1 plugin: code-graph-mcp.
Plugin Claude Code
Plugin marketplace listing 1 plugin: code-graph-mcp.
Plugin Claude Code
AST knowledge graph for intelligent code navigation — auto-indexes your codebase and provides semantic search, call graph traversal, HTTP route tracing, and impact analysis via MCP tools.
MCP server Claude CodeCodexCursor +2
MCP server "code-graph" as configured in sdsrss/code-graph-mcp. Runs ${CLAUDE_PLUGIN_ROOT}/scripts/mcp-launcher.js with node.
Agent
Deep code understanding expert using AST knowledge graph. Use when exploring unfamiliar code, tracing complex relationships, or understanding module architecture.
Hook
Runs when a session starts on startup, clear and compact, executing session-init.js via node. From sdsrss/code-graph-mcp.
Skill Claude CodeCodex
Audit and harden this Rust repo (code-graph-mcp) for Windows correctness: path-spelling drift between producers, the 32,767-char command-line cap, index-key mismatches, and path predicates that assume one ecosystem's layout. Use whenever touching code that builds, compares, prints, or stores a filesystem path; that…
Plugin Claude Code
Plugin marketplace listing 1 plugin: claude-mem-lite.
Plugin Claude Code
Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. A lighter, lower-cost alternative to claude-mem (episode batching + a smaller model; cost savings are an…
MCP server Claude CodeCodexCursor +2
MCP server "mem-lite" as configured in sdsrss/claude-mem-lite. Runs ${CLAUDE_PLUGIN_ROOT}/scripts/launch.mjs with node.
Instructions file
Instructions for sdsrss/claude-mem-lite, covering claude-mem-lite, quick reference, health stack, architecture and where new code goes (audit 2026-08-22 p2-7).
Command
Use when: user asks to increase claude-mem-lite's tool-invocation rate in the current project, or to (re)install the steering block. Writes a sentinel-wrapped managed block into /CLAUDE.md plus a /.claude/pluginclaudememlite.md detail doc, and migrates away any legacy memory-dir sentinel. Runs automatically on…
Command
Use when: logging a known bug + repro steps you can't fix right now. Writes a searchable observation (findable via memsearch + surfaced by recall hooks; still NOT memdir). Skip for bugs you're actively fixing in the current turn — just fix them.
Command
Use when: capturing a non-obvious lesson/gotcha/workaround after a tricky fix or surprising behavior. Writes a searchable observation (findable via memsearch + surfaced by recall hooks; still NOT memdir/L1 prompt). Skip for typos, renames, or user-preference rules.
Command
Use when: querying past work, managing memories, or checking project history.
Command
Use when: user asks to remember something, after solving a non-obvious problem, or to capture key session findings.
Command
Use when: importing skills/agents from GitHub, managing registry resources, or searching for tools to solve a problem.
Command
Use when: user wants to remove the claude-mem-lite steering block from the current project (or from every project Claude Code knows about with --all). Removes the /CLAUDE.md managed block + /.claude/pluginclaudememlite.md and cleans any legacy memory-dir residue. User content outside the sentinel is preserved. Benign…
Command
Use when: search results seem noisy, after bulk imports, or for periodic memory/registry maintenance.
Hook
Runs when a session starts on startup, clear and compact, executing setup.sh and hook-launcher.mjs via bash (2 commands). From sdsrss/claude-mem-lite.
Hook
Runs before the context is compacted, executing hook-launcher.mjs via node. From sdsrss/claude-mem-lite.
Hook
Runs before the agent uses a tool for Edit, Write, NotebookEdit, Read, Skill, Agent and Task tool calls, executing hook-launcher.mjs and pre-agent-inject.sh via node (3 commands). From sdsrss/claude-mem-lite.
Hook
Runs after a tool call finishes for Edit, Write and NotebookEdit tool calls, executing post-tool-use.sh and hook-launcher.mjs via bash (2 commands). From sdsrss/claude-mem-lite.
Hook
Runs when a tool call fails for Bash tool calls, executing hook-launcher.mjs via node. From sdsrss/claude-mem-lite.
Hook
Runs when the agent finishes a response, executing hook-launcher.mjs via node. From sdsrss/claude-mem-lite.