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.
/plugin marketplace add miltonian/cartographernpx agentmods add plugins/miltonian/cartographer/plugingit clone --depth 1 https://github.com/miltonian/cartographerGrade A, and why
cartographer 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": "cartographer",
"version": "0.8.0",
"description": "Agent-first code understanding system. Builds a persistent world-model of your codebase with evidence-grounded facts, semantic map, behavior flows, perspectives, PR review overlay, and navigable depth via semantic zoom.",
"author": {
"name": "Alexander Hamilton",
"email": "[email protected]"
},
"homepage": "https://github.com/miltonian/cartographer",
"repository": "https://github.com/miltonian/cartographer",
"license": "MIT",
"keywords": [
"code-understanding",
"world-model",
"semantic-map",
"codebase-visualization",
"evidence-grounded"
]
}
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 · 20 lines scan A d650e267442c
cartographer is a plugin published in the GitHub repository miltonian/cartographer (1 stars, last pushed 2mo 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
devlens
Codebase intelligence for AI agents. The /devlens skill teaches your agent to query a precomputed code graph (nodes, typed edges, technical/business/security summaries) via the bundled DevLens MCP server instead of grepping and reading whole files — for TypeScript, JavaScript, Python, Go, Rust, and Java repos, with…
devlensio
DevLens plugins — codebase intelligence for AI agents.
desktop-commander
MCP server for terminal commands, process management, and file operations across text files, code, PDF, DOCX, Excel, images, and structured data.
desktop-commander
Plugin marketplace listing 1 plugin: desktop-commander.
ai-doc-gen
Multi-agent codebase analysis and documentation generation: parallel analyzers for structure, dependencies, data flow, request flow, and APIs, plus README and AI-rules (CLAUDE.md, AGENTS.md, Cursor rules) generators.
roslyn-codelens
Roslyn-based code graph intelligence for .NET codebases. Requires .NET 10 SDK and the global tool: dotnet tool install -g RoslynCodeLens.Mcp.