An architectural monitoring add-on for AI coding agents. It scans a codebase and tracks structural changes such as coupling, dependency cycles, and the likely impact of edits.

Use it at the start of a coding session, before edits to assess blast radius, after edits to compare regressions, or for architecture and drift audits.

It gives agents a baseline before changes and evidence afterward, making architectural regressions and unintended effects easier to spot.

raysense — Plugin for Claude Code by RayforceDB

Install

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.

Clone the repo

git clone --depth 1 https://github.com/RayforceDB/raysense

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/rayforcedb/raysense/claude-plugin/github.svg)](https://agentmods.dev/plugins/rayforcedb/raysense/claude-plugin)

Your own site

<a href="https://agentmods.dev/plugins/rayforcedb/raysense/claude-plugin"><img src="https://agentmods.dev/badge/plugins/rayforcedb/raysense/claude-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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/rayforcedb/raysense/claude-plugin"><img src="https://agentmods.dev/badge/plugins/rayforcedb/raysense/claude-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 6 skills, 6 commands, 1 MCP server cost 591 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

raysense 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.

claude-plugin/.claude-plugin/plugin.json · 25 lines

What it actually says

{
  "name": "raysense",
  "version": "0.5.0",
  "description": "Architectural telemetry for AI coding agents. Phase-scoped skills + slash commands over the raysense MCP server: scan + baseline at session start, blast-radius before edits, regression diff after, on-demand architecture audits, time-window drift detection.",
  "author": {
    "name": "Anton Kundenko",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/RayforceDB/raysense",
  "repository": "https://github.com/RayforceDB/raysense",
  "license": "MIT",
  "keywords": [
    "architecture",
    "code-quality",
    "mcp",
    "agent-loop",
    "structural-health",
    "coupling",
    "cycles",
    "blast-radius",
    "memory",
    "raysense"
  ]
}

Contents

What it installs

The manifest is a name and a version. 6 skills, 6 commands, 1 MCP server travel with it, and installing the plugin installs all of them — 591 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

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 · 25 lines scan A d033918a4a85

Subscribe to this mod's changes

raysense is a plugin published in the GitHub repository RayforceDB/raysense (13 stars, last pushed 5mo 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.

Claude Code Debugging ai-agents claude-agent code-architecture code-quality dependency-graph

brooks-lint

AI code reviews grounded in twelve classic engineering books — decay risk diagnostics with book citations, severity labels, and six analysis modes (PR review, architecture audit, tech debt, test quality, health dashboard, full-sweep auto-fix).

hyhmrright/brooks-lint · not measured

fuse-changelog

Claude Code update watcher: changelog tracking, breaking changes detection, community pulse via Exa, plugin compatibility analysis.

fusengine/agents · not measured

antidote

Stop AI agents from patching symptoms. Forces structural root-cause fixes over symptom patching in any language or stack.

Avtr99/antidote · not measured

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…

skymanbp/CodeEraser · not measured

vg

Vibgrate AI Context for Claude Code: a local-first MCP server with a deterministic code map (impact, navigation, search) plus version-correct, drift-annotated library docs. No API key.

vibgrate/cli · not measured

n1-optimizer

Parallel performance analysis tool that identifies N+1 queries, inefficient APIs, and suboptimal code patterns across your entire application stack.

hculap/better-code · not measured