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/agentic-research/macheWrote 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/agentic-research/mache/plugin)<a href="https://agentmods.dev/plugins/agentic-research/mache/plugin"><img src="https://agentmods.dev/badge/plugins/agentic-research/mache/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/agentic-research/mache/plugin"><img src="https://agentmods.dev/badge/plugins/agentic-research/mache/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
mache 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
{
"name": "mache",
"version": "0.1.0",
"description": "Structured code index — browse, search, and trace dependencies via MCP tools powered by mache",
"author": {
"name": "Agentic Research",
"url": "https://github.com/agentic-research"
},
"repository": "https://github.com/agentic-research/mache",
"license": "Apache-2.0",
"keywords": ["code-index", "mcp", "tree-sitter", "code-graph", "dependencies"]
}
What it installs
The manifest is a name and a version. 3 skills, 1 agent travel with it, and installing the plugin installs all of them — 321 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.
- 1mo ago First seen · 13 lines scan A 78bf22d4ec7e
mache is a plugin published in the GitHub repository agentic-research/mache (46 stars, last pushed today), licensed Apache-2.0. 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
codanna-toolset
Codanna toolset for Claude Code: x-ray (semantic search + relationship traversal with 3D neighbourhood, radial tree and edge-bundle views) and graph (the whole index as a module disc with hubs at the centre, timeline and heatmap). Needs the codanna CLI.
repowise
Codebase intelligence for Claude Code. Indexes your codebase into five layers (Graph, Git, Docs, Decisions, Code Health) and exposes them through task-shaped MCP tools, so Claude understands architecture, ownership, hotspots, why code is built the way it is, and where the defect risk lives.
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.
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.
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.
reposkein
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.