claude

research-toolkit

Investigation protocols, dialectic verification, frame rotation, financial analysis (STONK), video/substack research. Includes financial-mcp.

0 on GitHubby bogheorghiuv3.1.0updated 2 months ago
/

Plugin research-toolkit from marketplace ex-cog in bogheorghiu/ex-cog. Commands read from the repo's manifest — 1 month ago.

What it installs

Skills (14)

  • cui-bono

    Who actually benefits — and at whose expense? Power structure analysis for any domain: geopolitics, corporate behavior, institutional claims, media narratives. Use when (1) who benefits from X, (2) ownership or revolving doors, (3) are these sources independent or echoing one origin, (4) expert has

  • deep-investigation-protocol

    What is REALLY at stake here? And for whom?" - STOP. When the matter involves trustworthiness, purchasing decisions, "which is better or more reliable", brand comparisons, marketing claims, corporate behavior, "convince me otherwise", or post-purchase "was this good?" - USE THIS. For technical specs

  • dialectic-spiral

    Am I agreeing because it SOUNDS right, or because it IS right? Recursive adversarial dialectic for testing any claim, finding, or synthesis against its own opposite. Use when convergence feels too easy, when findings need stress-testing, or when any research skill escalates to dialectic depth.

  • frame-rotation

    「透镜」 What structure hides in my native grammar? Linguistic frame rotation to escape English-default pattern-recognition. Use when (1) pattern-recognition feels stuck in familiar grooves, (2) abstraction circles without grounding, (3) cross-domain insight feels like same-OS-different-domain, (4) trig

  • iterative-verification

    Is this ACTUALLY verified, or did I just say it is?" - Ralph-wiggum methodology applied to factual accuracy. Use when (1) claims require evidence not assumption, (2) verification must be demonstrable, (3) single-pass investigation insufficient, (4) factual accuracy is critical. Provides the loop log

  • macro-monitor

    What is moving in the macro picture? Geopolitical/macro market indicators. Use when (1) China/US Treasury dynamics, (2) dollar-yield divergence, (3) Brent crude oil / energy price spikes, (4) geopolitical market risk, (5) one-command crisis check. NOT for stock analysis or fundamentals.

  • manufactured-consensus-detection

    Are these sources agreeing independently, or echoing the same origin?" - When multiple sources converge on the same claim in similar language, test whether this is genuine independent agreement or coordinated messaging from a single origin. Use when (1) multiple independent sources say the same thin

  • research

    Where should I start investigating this? Routes research questions to the right methodology based on topic domain, depth needed, and available sources. Use when the research question spans multiple domains or the appropriate methodology is unclear. Not needed when a specific skill (DIP, cui-bono, yo

  • source-omission-analysis

    What is everyone NOT saying about this?" - After any multi-source research sweep, analyze what each perspective is SILENT about. Omissions reveal structural position more reliably than statements. Use when (1) after completing multi-source research, (2) comparing coverage across ideological position

  • stonk

    Who actually benefits — and at whose expense? Power structure analysis for investment decisions, geopolitical positioning, corporate behavior, and any question where money flows, ethical constraints, or multi-polar dynamics matter. Triggers on: corporate complicity analysis, weapons/military connect

  • substack-research

    What are the independent voices actually saying? Extract and analyze long-form content from Substack publications. Use when (1) researching independent journalist perspectives, (2) analyzing a specific Substack publication, (3) building a research corpus from long-form written content, (4) cross-ref

  • text-deconstruction

    Where does this text need what it excludes? Finds where texts undermine themselves on their own terms via close reading. Use when (1) analyzing arguments, policies, or frameworks claiming coherence, (2) something feels off but unnameable, (3) a framework presents itself as complete, (4) user asks wh

  • video-transcript-extraction

    How do I get the transcript of this video? Platform-aware extraction for any video source — YouTube, local files, or other platforms. Use when (1) need to transcribe a video for analysis, (2) user provides a video URL, (3) building a knowledge base from video content. Provides multiple methods with

  • youtube-research

    What do practitioners actually DO (not just document)? Methodology for extracting practitioner knowledge from YouTube video transcripts. Use when (1) researching how people actually use a technology, (2) seeking practitioner insights beyond documentation, (3) looking for tips, patterns, or workflows

Slash commands (1)

  • /research-toolkit:substack-extract

    Extract and parse Substack articles with AI analysis

Subagents (5)

  • adversarial-critic

    Did I just agree because it SOUNDED right?" - Adversarial critic for investigation teams. Reads researchers' output files and runs the generative dialectic spiral — generating the exact OPPOSITE of each synthesis, then testing it. Use when (1) investigation teams need adversarial challenge, (2) find

  • falsifier

    What here is NOT actually working?" - Adversarial verification agent that seeks disconfirmation. Designs and runs falsification tests against claims, implementations, and completion criteria. Use when (1) verifying implementation claims match reality, (2) stress-testing completion criteria before ma

  • investigation-orchestrator

    Who needs to look at this, from where, and what are they not seeing?" - Orchestrates full multi-agent investigations. Takes a topic, designs the team, assigns source-position scopes, deploys researchers + adversarial critic, manages dialectic rounds, and produces final synthesis with evidence tiers

  • negative-dialectical-spiral

    Hold the contradiction open — do not resolve. Maps where concepts fail against particulars via context-isolated tension tracking. Use when (1) synthesis feels too neat, (2) need what a frame cannot capture, (3) dialectic-spiral resolves when it should hold open. NOT for binary questions, stress-test

  • release-tagger

    Is this worth marking as stable?" - Helps prepare tagged releases for ex-cog plugins. Use when (1) preparing a stable release before breaking changes, (2) user says "tag this" or "stable release", (3) major milestone worth preserving. Guides through git tagging and publish workflow.

View source on GitHub

More from bogheorghiu/ex-cog

All 4 plugins →

Pattern recognition across unrelated contexts. Observe, record, test, and browse behavioral patterns. Includes relational-memory and edge-graph MCPs.

11 skills · 1 command · 1 agent · hooks

0

Budget-conscious agent identity — efficiency as capability, not constraint. Loosely based on BATS framework research.

2 skills · 1 agent

0

Prompt-injection detection hook with tiered HIGH/LOW confidence and env-var-driven allowlist. Covers MCP tool outputs via the * matcher. (Stable subset; full plugin with git/Desktop-Commander blocking lives in bogheorghiu/ex-cog-dev.)

hooks

0

Maintain research-toolkit?

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 plugins4 plugins