agentmods.dev

deep

A plugin for discovering, planning, and implementing complex software systems with research, architecture work, test-driven development (TDD), and review by multiple language models. TDD means writing tests as part of guiding the implementation.

In plain words
What is it for?
Use it for system design, build-versus-buy decisions, architecture planning, complex implementation, and projects where tests and independent AI review are part of the process.
Why use it?
It organizes difficult engineering work into research, design, review, and implementation steps, helping address problems that need more than a quick code change.

Plugin for Claude Code

2 3d ago A scan tokens not measured original MIT
View the source file kbichave/skills
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.

Claude Code
/plugin marketplace add kbichave/skills
agentmods
npx agentmods add plugins/kbichave/skills/skills
Clone the repo
git clone --depth 1 https://github.com/kbichave/skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 4 skills, 16 agents, 6 hooks cost 1,595 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

deep 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 2d 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/plugin.json · 13 lines

What it actually says

{
  "name": "deep",
  "description": "Discover, plan, and implement complex systems with AI-assisted research, multi-LLM review, TDD sections, and disciplined execution",
  "version": "5.15.0",
  "author": {
    "name": "kbichave",
    "url": "https://github.com/kbichave"
  },
  "repository": "https://github.com/kbichave/skills",
  "license": "MIT",
  "keywords": ["planning", "implementation", "tdd", "architecture", "llm-review", "execution", "discovery", "system-design", "build-vs-buy"]
}
Contents

What it installs

The manifest is a name and a version. 4 skills, 16 agents, 6 hooks travel with it, and installing the plugin installs all of them — 1,595 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 2d ago First seen · 13 lines scan A 2fd5f97b9a91

Subscribe to this mod's changes

deep is a plugin published in the GitHub repository kbichave/skills (2 stars, last pushed 3d 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.

Building agentsPlanningai-planningclaude-codeclaude-code-pluginimplementation planningmulti-llm
Related

Other plugins, from other repositories

council

18 AI personas deliberate your hardest decisions — structured multi-round deliberation (blind analysis, anonymized cross-examination, weighted verdict) with genuine model diversity across providers.

0xNyk/council-of-high-intelligence · not measured

map-framework

Modular Agentic Planner (MAP) - Cognitive architecture for AI agents with 11 specialized agents and professional code review integration.

azalio/map-framework · not measured

universal-planning-framework

Planning framework for Claude Code that catches gaps before execution: a 10-step pipeline, 21 anti-patterns with detection rules, mandatory FAILED conditions, and silent execution-vehicle selection.

primeline-ai/universal-planning-framework · not measured

inspectrum

Automatic, bounded, fail-open Codex review before Claude Code approval; final approval stays yours.

yannmenec/inspectrum · not measured

fathom

Planning session mode for complex tasks. Enter Fathom Mode to build shared understanding through structured dialogue before execution. Use this when you want to plan, think through, or clarify something complex before acting on it.

ma-ziwei/fathom-mode-for-claude · not measured

notion-skills

Collection of Claude skills for productive Notion workflows including knowledge capture, meeting intelligence, research documentation, and specification-to-implementation planning.

tommy-ca/notion-skills · not measured