claude

deep-think

Structured reasoning with auto-checkpointing, branching, and reflection

1 on GitHubby Ioan-Sorin Baicoianuv1.1.2MITupdated 2 months ago
/

Plugin deep-think from marketplace bis-code-deep-think in bis-code/mcp-deep-think. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.

What it installs

Skills (3)

  • manage-constraints

    Use when the user conversationally asks to add reasoning rules, constraints, or anti-patterns to their deep-think configuration. Triggers on phrases like "remember to always check X", "add a rule about Y", "from now on check Z during reasoning", "never do X when thinking through problems".

  • manage-practices

    Use when the user conversationally asks to add review checklist items, custom reasoning strategies, or modify their deep-think review process. Triggers on phrases like "add a review step for...", "create a strategy for...", "I want to always check for... during review", "add a custom thinking framew

  • restore-checkpoint

    Use when starting a new session and the user seems to be continuing previous reasoning work, mentions resuming a thought chain, or asks to restore a deep-think checkpoint. Also triggers when a user mentions picking up where they left off on a complex decision or analysis.

Slash commands (4)

  • /deep-think:checkpoints

    View, restore, or delete saved deep-think reasoning checkpoints

  • /deep-think:constraints

    Manage reasoning rules and anti-patterns in .deep-think.json

  • /deep-think:practices

    Manage review checklists and custom strategies in .deep-think.json

  • /deep-think:start

    Launch a deep-think reasoning session from a natural language description

MCP servers (1)

  • deep-think

    runs: node ${CLAUDE_PLUGIN_ROOT}/server/dist/bundle.mjs

Hooks (1)

  • PreCompact
View source on GitHub

Similar plugins

Appends two or three short follow-up questions after a substantive answer to help users check key facts, probe the reasoning, and notice missing context

19 skills

anthropics/skills 193,780

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

Scaffold, validate, and publish new Claude Code plugins with proper structure

3 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

marketing-skills

claudecodex

53 marketing skills for technical marketers and founders: CRO, copywriting, cold email, prospecting, SEO, AI SEO, paid ads, SMS, ad creative, video production, image generation, co-marketing, churn prevention, pricing, referrals, revenue operations, sales enablement, customer research, site architecture, comprehensive AARRR-structured marketing plans, public relations and earned media, offer design, event marketing and webinars, and more

53 skills

coreyhaines31/marketingskills 59,996

Web scraping, Google search, structured data extraction, and MCP server integration powered by Bright Data. Includes 7 skills: scrape any webpage as markdown (with bot detection/CAPTCHA bypass), search Google with structured JSON results, extract data from 40+ websites (Amazon, LinkedIn, Instagram, TikTok, YouTube, and more), orchestrate Bright Data's 60+ MCP tools, built-in best practices for Web Unlocker, SERP API, Web Scraper API, and Browser API, Python SDK best practices for the brightda...

21 skills

anthropics/claude-plugins-official 47,076

ifixai

claudecodex

Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).

1 skill · hooks

ifixai-ai/iFixAi 45,158

Maintain deep-think?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex pluginslisted