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/tosin2013/mcp-adr-analysis-serverWrote 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/tosin2013/mcp-adr-analysis-server/document-specialist)<a href="https://agentmods.dev/plugins/tosin2013/mcp-adr-analysis-server/document-specialist"><img src="https://agentmods.dev/badge/plugins/tosin2013/mcp-adr-analysis-server/document-specialist/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/tosin2013/mcp-adr-analysis-server/document-specialist"><img src="https://agentmods.dev/badge/plugins/tosin2013/mcp-adr-analysis-server/document-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
document-specialist 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 29d 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": "document-specialist",
"version": "3.3.0",
"description": "Write DESIGN_DOC.md, architecture docs, SRS, and diagrams in Cursor. Mermaid first. PlantUML leftover types.",
"author": {
"name": "Spillwave Solutions",
"email": "[email protected]",
"url": "https://spillwave.com"
},
"homepage": "https://github.com/SpillwaveSolutions/document-specialist-skill",
"repository": "https://github.com/SpillwaveSolutions/document-specialist-skill",
"license": "MIT",
"keywords": [
"documentation",
"sdd",
"architecture",
"mermaid",
"cursor"
],
"skills": "./skills/"
}
What it installs
The manifest is a name and a version. 2 skills, 4 commands travel with it, and installing the plugin installs all of them — 398 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.
- 29d ago First seen · 22 lines scan A 4d64fba9025f
document-specialist is a plugin published in the GitHub repository tosin2013/mcp-adr-analysis-server (35 stars, last pushed yesterday), 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 2026-09-17.
Other plugins, from other repositories
ai-software-architect
AI-powered architecture documentation framework with ADRs, reviews, and pragmatic mode.
adrkit
Load the architecture decisions governing a change, check plans against them, audit existing code and documentation for missing decisions, draft new records deliberately, and (in GitHub Copilot CLI) run an advisory adr-review workflow, and open a read-only decision-review canvas in the GitHub Copilot app — driven by…
agent-decision-record
Structured decision-making for AI coding agents. Creates auditable Agent Decision Records (AgDR) when technical choices are made — selecting libraries, patterns, or architecture.
archsteer
Architecture governance for AI coding agents — derive the real architecture from any repo, enforce declared rules with a net-new ratchet, and stop agents drifting off pattern before code ships.
vibeframe
A control plane for agentic coding: a living, in-repo model of intent, architecture, and code — deterministically indexed, bidirectionally linked, continuously drift-checked. Bundles the VibeFrame MCP server, deterministic hooks, and workflow commands.
bleu
Claude Code plugin for living blueprints. Turn an idea into a deeply structured, lint-passing, file-backed system plan before writing any code.