A collection of coding-agent skills for turning product ideas into defined requirements and then carrying settled ideas through implementation and review.

Use it to clarify an idea into a CRAFT.md brief, or run a feature from agreed requirements through a finished code branch.

It separates unclear product decisions from coding work and coordinates questions, approvals, parallel work, reviews, and fixes in one recorded process.

superb — Plugin for Claude Code by kardebadas/claude-plugin

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/kardebadas/claude-plugin

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/kardebadas/claude-plugin/superb/github.svg)](https://agentmods.dev/plugins/kardebadas/claude-plugin/superb)

Your own site

<a href="https://agentmods.dev/plugins/kardebadas/claude-plugin/superb"><img src="https://agentmods.dev/badge/plugins/kardebadas/claude-plugin/superb/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/kardebadas/claude-plugin/superb"><img src="https://agentmods.dev/badge/plugins/kardebadas/claude-plugin/superb.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 8 skills, 5 agents cost 942 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

superb 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 17d 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/superb/.claude-plugin/plugin.json · 34 lines

What it actually says

{
  "name": "superb",
  "version": "0.16.0",
  "description": "Personal skill collection for Claude Code and Codex, invoked as superb:<skill>. 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 same with one human gate, resolving later decisions by a three-agent quorum that may never overrule a recorded human answer; fast-pipeline trades tests and review layers for speed, with one spec approval and a final review/bug-fix loop; turbo-pipeline asks one batch of at most six questions and then builds autonomously, settling later decisions by two independent brains whose higher confidence wins; bug-investigate finds out why something is broken and stops there; bug-fix carries it on to a regression-tested fix.",
  "author": {
    "name": "kardebadas"
  },
  "keywords": [
    "setup",
    "dependencies",
    "craft",
    "product-discovery",
    "requirements",
    "design",
    "pipeline",
    "orchestration",
    "planning",
    "code-review",
    "subagents",
    "parallel",
    "autonomous",
    "pipeline-auto",
    "quorum",
    "fast-pipeline",
    "turbo-pipeline",
    "two-brain",
    "bug-investigate",
    "diagnosis",
    "bug-fix",
    "debugging",
    "root-cause"
  ]
}

Contents

What it installs

The manifest is a name and a version. 8 skills, 5 agents travel with it, and installing the plugin installs all of them — 942 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.

17d ago Changed · +3 lines fe11cf000145
21d ago Changed · +2 lines 6272079bb7cd
1mo ago Changed b7c6f6996429
1mo ago Changed 0ca3bdb19f5b
1mo ago Changed a347104efae6
1mo ago Changed 321e48db1229
1mo ago Changed · +8 lines 00044cf49dde
1mo ago First seen · 21 lines scan A 2bb4f4f85c78

Subscribe to this mod's changes

superb is a plugin published in the GitHub repository kardebadas/claude-plugin (3 stars, last pushed 18d ago), 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 2026-08-31.

Building agents Planning claude-code-plugin claude-code-skills claude-plugin claude-skills codex-cli codex-plugin

superb

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

What it actually says

What it installs

What this file has done since we first saw it

Other plugins, from other repositories

neatcontext marketplace

neatcontext

apple-dev-skills

agent-portability-skills

agent-engineering-skills

android-dev-skills