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.
npx agentmods add plugins/munhq/codeindex/plugin/plugin marketplace add munhq/codeindexgit clone --depth 1 https://github.com/munhq/codeindexGrade A, and why
codeindex 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 yesterday.
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
{
"name": "codeindex",
"description": "Skills that teach any agent to answer code questions structurally instead of reading whole files \u2014 symbol lookup, callers, imports and blast radius. Bundles the codeindex MCP server so install wires everything in one step.",
"version": "0.3.5",
"author": {
"name": "munhq"
},
"homepage": "https://github.com/munhq/codeindex",
"repository": "https://github.com/munhq/codeindex",
"license": "MIT",
"keywords": [
"code-intelligence",
"symbols",
"tree-sitter",
"context",
"mcp"
]
}
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.
- yesterday First seen · 19 lines scan A 40394a65f45a
codeindex is a plugin published in the GitHub repository munhq/codeindex (3 stars, last pushed 3d 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 2026-08-31.
Other plugins, from other repositories
skills
400+ snow MCP tools for ServiceNow, plus the 70 skill guides that teach an agent to use them.
sverklo-skill
Teaches Claude how to use sverklo's code intelligence MCP tools — semantic search, blast-radius, PR review, codebase audit, persistent memory.
blockwatch
Keep co-dependent code, docs, and config in sync with BlockWatch annotations: drift detection (affects), sorted/unique lists, regex/line-count/AI/Lua validation. Includes a skill that teaches agents when and how to add and maintain blocks.
mako-ai
Project intelligence skills for Claude Code. Teaches Claude when to use Mako's MCP tools (context packets, code and schema search, diagnostics, RLS audits) instead of grep-walking the repo.
roxyapi
RoxyAPI multi domain spiritual intelligence API and Remote MCP for Claude Code. Auto connects the keyless Docs MCP and ships a skill that teaches Claude how to build natal charts, Vedic kundli, forecasts, human design, Chinese astrology, feng shui, numerology, tarot, and more, all under one key.
just-study
Plugin marketplace listing 1 plugin: just-study.