14 tagged code-graph, measured the same way as everything else here.
Plugin Claude Code
Bundles 9 skills, 1 MCP server · 510 tokens together
Local codebase intelligence + change-safety gates for coding agents. REQUIRES Python 3.10+ and pip install roam-code first — this plugin launches the roam binary from your PATH, and its MCP server cannot start without it. Pre-indexes your repo's symbols, call graph, deps, and git history into SQLite (28 languages.
Plugin Claude Code
Bundles 1 skill, 1 hook, 1 MCP server · 64 tokens together
98% fewer context tokens for your coding agent to find code — a queryable, PageRank-ranked ts-morph import/symbol map for TS/JS repos. Bundles the PreToolUse grep nudge, the navigation skill, and a stdio MCP server exposing 11 query tools including a compiler-accurate call graph, BM25 lexical search, plus CLI-only Mer.
Plugin Claude Code
Give your agent runtime evidence: semantic code search, dead-code detection, and fault localization over real runs — zero code changes (Python).
Plugin Claude Code
Bundles 3 commands, 9 hooks · 60 tokens together
Kage manages your memory and agents. It briefs and runs agents in isolated git worktrees for a single run or a multi-wave goal, re-runs the checks itself instead of trusting the agent's report, and remembers what it learns so each brief is smarter than the last.
Plugin Claude Code
Bundles 1 skill · 52 tokens together
CodeStory grounding for coding agents over the local codestory-cli runtime.
Plugin Claude Code
Bundles 1 skill, 1 MCP server, 1 plugin · 76 tokens together
Agentic PR review: hybrid RAG + code graph via MCP, review skills for Claude Code.
Plugin Claude Code
Bundles 5 skills · 187 tokens together
Graph-first AI coding workflow: Plan, Propose, Apply, Review, Archive with OpenSpec gates, evidence-based agents, and guardrail hooks.
Plugin Claude Code
Bundles 2 skills · 124 tokens together
Deterministic code-graph MCP server: structural navigation, semantic find, impact analysis, and architecture decision records for the current repo. Zero infrastructure — the graph lives in .reposkein/ and the indexer binary is fetched on first run.
Plugin Cursor
Bundles 2 skills, 2 MCP servers · 216 tokens together
Evidence infrastructure for AI software agents: 67 read-only repository intelligence tools through MCP.
Plugin Claude Code
Bundles 1 skill · 74 tokens together
Token-efficient code-understanding harness. Routes structural questions (callers, callees, impact, inheritors) to a prebuilt code graph instead of repeated grep and file-reads, cutting cumulative context tokens. Type /token-master in a repo to build the index and turn on routing.
Plugin Claude Code
Bundles 1 skill, 1 agent, 3 hooks · 251 tokens together
Search and read code across your organisation's repositories through a Celmis server: ranked symbol search, outlines, callers, and 'do it like service X' patterns, all with a token budget and no secret values.
meemoprasad/meeba-brain-marketplace
Plugin Cursor
Ground-truth code graph context for your own private codebase — exact callers, callees, symbol definitions, and file dependencies, from a real parsed graph, not text-similarity guessing.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 101 tokens together
Hybrid search + code graph + semantic memory for Claude Code, via the nexus-mcp-ci pip package. Requires pip install nexus-mcp-ci first — this plugin registers the MCP server and teaches Claude when to use it, it does not install the Python package.