Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/dvcdsys/code-indexWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/dvcdsys/code-index/cix)<a href="https://agentmods.dev/plugins/dvcdsys/code-index/cix"><img src="https://agentmods.dev/badge/plugins/dvcdsys/code-index/cix/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/dvcdsys/code-index/cix"><img src="https://agentmods.dev/badge/plugins/dvcdsys/code-index/cix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cix scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "cix",
"version": "0.4.0",
"description": "Semantic code search for Claude Code. Requires a self-hosted cix (CodeIndeX) server — free, MIT, ~10-minute install (https://codeindex.app) on your machine, LAN box, or GPU server; the plugin is the client. Ships the cix CLI, slash commands (incl. cix file / cix tree for external projects), behavioral hooks, the cix skill, plus the experimental cix-workspace skill and cix-workspace-investigator sub-agent for cross-project research.",
"author": {
"name": "dvcdsys",
"email": "[email protected]"
},
"homepage": "https://github.com/dvcdsys/code-index",
"repository": "https://github.com/dvcdsys/code-index",
"license": "MIT",
"keywords": [
"search",
"self-hosted",
"code-search",
"semantic",
"navigation",
"indexing",
"embeddings",
"ai",
"workspace",
"cross-project",
"monorepo",
"sub-agent"
]
}
What it installs
The manifest is a name and a version. 8 commands, 5 hooks travel with it, and installing the plugin installs all of them — 134 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command file A 19 tokens
- Command tree A 16 tokens
- Command init A 19 tokens
- Command search A 16 tokens
- Command def A 17 tokens
- Command refs A 17 tokens
- Command status A 14 tokens
- Command summary A 16 tokens
- Hook PostToolUse A not measured
- Hook CwdChanged A not measured
- Hook SessionEnd A not measured
- Hook SessionStart A not measured
- Hook PostCompact A not measured
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 28 lines scan A 23451be0dcd8
cix is a plugin published in the GitHub repository dvcdsys/code-index (30 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
gograph
Claude Code workflow guidance for local gograph: AST-aware call graphs, impact, security-flow candidates, and 61 query, analysis, and workflow capabilities through a separately registered MCP server.
cocosearch
Local-first hybrid semantic code search with dependency graphs and cross-repo search. Powered by CocoIndex, Tree-sitter, pgvector, and Ollama.
sqry
AST-based semantic code search (compiler-grade, not embeddings). Skills + MCP (sqry-mcp) + LSP (sqry-lsp) for Grok Build, Claude Code, and compatible agents. 37 languages, 39 tools, live resources from sqry-mcp binary.
codebase-index
Give Claude a precise local map of your codebase: find implementations, trace behavior, and predict change impact with file-line evidence.
pluck
Fast and token-friendly code reading for AI coding agents. Symbol-aware MCP tools that replace cat/grep with 85% fewer tokens, sub-millisecond search, and a raw fallback that preserves cat/grep parity byte-for-byte.
jarvis
Local-first structural code intelligence over your own indexed repositories, with skills that teach Claude to prefer structural queries over grep.