A brainstorming plugin that asks several isolated reasoning branches to explore an idea from different perspectives, then compares and develops the better options.

Use it for architecture choices, names, API designs, unclear debugging problems, and strategy.

It helps avoid settling too quickly on the first reasonable answer when a problem has several possible designs.

think — Plugin by mayank-io

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 mayank-io/mstack

agentmods

npx agentmods add plugins/mayank-io/mstack/think

Clone the repo

git clone --depth 1 https://github.com/mayank-io/mstack

Made for: Claude Code.

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

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

think 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 yesterday.

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/think/.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "think",
  "description": "Parallel divergent ideation for coding agents. The `adhd` skill spawns N isolated reasoning branches under different cognitive frames, scores them, prunes traps, and deepens the survivors — escaping the premature convergence of single-pass reasoning. Reach for it on architecture, naming, API design, fuzzy debugging, and strategy. Vendored from UditAkhourii/adhd.",
  "author": {
    "name": "Udit Akhouri",
    "url": "https://github.com/UditAkhourii/adhd"
  },
  "license": "MIT",
  "keywords": [
    "ideation",
    "brainstorming",
    "divergent-thinking",
    "tree-of-thought",
    "reasoning",
    "architecture",
    "naming",
    "design"
  ]
}

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.

yesterday First seen · 20 lines scan A 91f11b584ba9

Subscribe to this mod's changes

think is a plugin published in the GitHub repository mayank-io/mstack (5 stars, last pushed 7d 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.

Backend and APIs Debugging Planning

think

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

nextjs

nextjs

claude-plugins-official

knowledge-work-plugins

ecc

ecc