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/munhq/codeindexWrote 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/munhq/codeindex/plugin)<a href="https://agentmods.dev/plugins/munhq/codeindex/plugin"><img src="https://agentmods.dev/badge/plugins/munhq/codeindex/plugin/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/munhq/codeindex/plugin"><img src="https://agentmods.dev/badge/plugins/munhq/codeindex/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade 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 19d 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
{
"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": "0.6.1",
"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"
],
"userConfig": {
"enforce": {
"type": "boolean",
"title": "Refuse a scan the index answers better",
"description": "On: an identifier search that is the whole command line is refused, and the agent is given the structural call that answers it. Never refuses a file read, never refuses a line that also builds or tests, and stops after three refusals in a session. Off: the hooks only advise.",
"default": true
}
}
}
What it installs
The manifest is a name and a version. 1 skill, 2 hooks, 1 MCP server travel with it, and installing the plugin installs all of them — 148 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 19d ago Changed 826ece31d169
- 20d ago Changed af7a9c26f84e
- 1mo ago Changed 60708221e500
- 1mo ago Changed f4aa1e7e7300
- 1mo ago Changed · +8 lines a7688ef85f3f
- 1mo ago First seen · 19 lines scan A 40394a65f45a
codeindex is a plugin published in the GitHub repository munhq/codeindex (3 stars, last pushed 6d 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
synapse-mcp
A persistent code-knowledge graph for AI agents. Runs locally. Writes safely.
weavatrix
Evidence infrastructure for AI software agents: 67 read-only repository intelligence tools through MCP.
trace-mcp
Framework-aware code intelligence MCP server. 88 framework integrations, 81 languages, semantic search with Signal Fusion (BM25 + PageRank + embeddings + identity), refactoring tools (rename/move/extract/codemod), change-impact analysis, security scanning, and decision/session memory.
narsil
Code intelligence plugin for narsil-mcp. Provides guidance for using 90 code analysis tools including security scanning, call graph analysis, symbol search, supply-chain SBOM, and SPARQL/CCG knowledge graph export.
codeeraser
CodeEraser passive guard + erase skill: a winnowing clone index behind a per-project daemon intercepts T1/T2 duplicate writes at PreToolUse (with the tombstone and flow legs judged in the core), records at PostToolUse whether an asked write ran (settle), audits net LOC + touched duplicates at Stop, and reports health…
omen-development
Code analysis skills for active development: find bugs, assess impact, plan refactoring, audit architecture, and more.