A Claude Code plugin that provides Cladding, a development framework for managing specification-led, multi-agent software work. It exposes project specifications, drift checks, events, and role instructions through an MCP server.

Use it to manage feature specifications, coordinate coding agents, detect differences between plans and implementation, and inspect development events in Claude Code.

It brings planning, agent coordination, audit records, and code-quality controls into a single Claude Code setup.

cladding — Plugin for Claude Code by qwerfunch

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/qwerfunch/cladding

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/qwerfunch/cladding/claude-code/github.svg)](https://agentmods.dev/plugins/qwerfunch/cladding/claude-code)

Your own site

<a href="https://agentmods.dev/plugins/qwerfunch/cladding/claude-code"><img src="https://agentmods.dev/badge/plugins/qwerfunch/cladding/claude-code/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/qwerfunch/cladding/claude-code"><img src="https://agentmods.dev/badge/plugins/qwerfunch/cladding/claude-code.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 1 command, 6 agents, 5 hooks cost 429 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

cladding 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.

plugins/claude-code/.claude-plugin/plugin.json · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "cladding",
  "version": "0.10.1",
  "description": "Reference implementation of the Ironclad standard — multi-agent dev harness for Claude Code.",
  "author": {
    "name": "qwerfunch"
  },
  "license": "MIT",
  "homepage": "https://github.com/qwerfunch/cladding",
  "repository": "https://github.com/qwerfunch/cladding.git",
  "keywords": [
    "harness",
    "harness-engineering",
    "spec-driven-development",
    "governance",
    "ironclad",
    "drift-detection",
    "multi-agent",
    "audit-trail",
    "code-quality",
    "compliance",
    "ai-coding",
    "architecture-enforcement",
    "claude-code",
    "mcp-server"
  ],
  "bugs": "https://github.com/qwerfunch/cladding/issues",
  "mcpServers": {
    "cladding": {
      "command": "node",
      "args": ["${CLAUDE_PLUGIN_ROOT}/dist/clad.js", "serve"],
      "description": "cladding MCP server — exposes spec / drift / events / personas as tools, resources, prompts. Runs the engine bundled with this plugin (no global `clad` on PATH required). Auto-starts when this plugin is enabled; no manual `claude mcp add` needed."
    }
  },
  "ironclad": {
    "spec-version": "0.0.23",
    "spec-url": "https://github.com/qwerfunch/ironclad",
    "spec-tag": "v0.0.23",
    "spec-commit": "883ff01d0360b7c989fe16214c69a324f049c8cd",
    "spec-fetched": "2026-05-18",
    "target": {
      "iron-law": "L4",
      "detectors": "41/41",
      "ears": "full"
    },
    "current": {
      "iron-law": "L4",
      "detectors": "41/41",
      "ears": "syntactic",
      "phase": "L21.12 — Territory → Integrity Panel rename (vocab anchored to Trinity of Integrity)",
      "stages-implemented": ["stage_1.1", "stage_1.2", "stage_1.3", "stage_1.4", "stage_1.5", "stage_1.6", "stage_2.1", "stage_2.2", "stage_2.3", "stage_2.4", "stage_3.1", "stage_3.2", "stage_3.3", "stage_4.1", "stage_4.2"],
      "spec-schema-version": "0.2",
      "conformance": {
        "level-1": {"declared-at": "2026-05-18", "fixtures": "12/12"},
        "

Read the full file on GitHub · 76 lines

Contents

What it installs

The manifest is a name and a version. 1 command, 6 agents, 5 hooks travel with it, and installing the plugin installs all of them — 429 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 Changed 8911c0441a4e
1mo ago Changed f5a49d4406a6
1mo ago First seen · 76 lines scan A 0b3e617b8d8e

Subscribe to this mod's changes

cladding is a plugin published in the GitHub repository qwerfunch/cladding (16 stars, last pushed 1mo 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.

Building agents Claude Code ai-coding claude-code-plugin codex-cli cursor-ide drift-detection

multi-cursor

Official Cursor SDK coding harness.

greenpolo/cc-multi-cli-plugin · not measured

lid-experimental

Experimental LID skills with opt-in installation and explicit lifecycle (promotion or retirement). Layers on top of linked-intent-dev and arrow-maintenance.

jszmajda/lid · not measured

commander-hub marketplace

Plugin marketplace listing 1 plugin: commander.

KevinZai/commander · not measured

dekko

Static code map for LLM agents. /map parses the repository with tree-sitter into MAP.md and map.json (every file, function, signature, type, and call edge) without spending model tokens; an 18-tool MCP server (searchcode, outline, querysymbol, getcallers, workset, impactedtests, ...) answers structural questions fr.

aahlijia/dekko · not measured

ratatoskr

A communication layer for your AI coding agent: plain language, no jargon, no invented timelines, and one clear yes before anything irreversible — shaping how the agent talks to you, not how it works.

krzysztofdudek/RatatoskrSkill · not measured

superb

Personal skill collection for Claude Code and Codex, invoked as superb: . setup installs what the others need; craft turns a vague product idea into a decision-rich brief; pipeline v2 drives a settled idea through approved file-backed plans and durable execution state to a finished branch; pipeline-auto does the.

kardebadas/claude-plugin · not measured