Stats

Actions

Available In

Tags

behavior-diagnostics - Claude Code Plugin | ClaudePluginHub

Plugin

behavior-diagnostics

Debug AI tooling behavior by analyzing output against source instructions and enabling honest self-diagnosis.

What's Inside

Skills2

This skill should be used when the user asks to "diagnose this output", "debug this behavior", "analyze what went wrong", "perform root cause analysis", "why did the agent do this", mentions unexpected AI tooling output, or needs to understand why a skill, agent, or command deviated from its intended behavior. Provides gap analysis and targeted introspection questions against source instructions.

This skill should be used when the user pastes diagnostic questions, says "introspect", "answer these questions about your behavior", "explain why you did this", "reflect on your behavior", or provides questions generated by the diagnosing skill. Answers introspection questions about session behavior with complete honesty for behavior diagnostics workflows.

README

ITB AI Tools

A collection of AI coding and productivity tools — skills, agents, hooks, and more — for Claude Code, Codex, and other AI coding assistants.

Installation

Add this marketplace to Claude Code:

/plugin marketplace add it-bens/ai-tools

Then browse and install plugins:

/plugin

Available Plugins

Plugin	Description	Category
llm-author	Author LLM-targeted content — prompts, skills, agents, and rules files — for Claude 4, GLM 4.7, and Gemini 3	Productivity
python-plan-optimizer	Analyze Python code in planning documents for design principles and improvement opportunities	Development
native-tools-enforcer	Enforces native search tools (Grep/Glob on classic builds, bfs/ugrep on native macOS/Linux) via PreToolUse hook; SessionStart hook primes Claude with mode-appropriate directives; setup skill installs binaries and configures mode	Guardrails
explore-with-sonnet-enforcer	Enforces Sonnet model for Explore subagent to prevent lossy Haiku summaries	Guardrails
explore-with-opus-enforcer	Enforces Opus model for Explore subagent for maximum exploration accuracy	Guardrails
plan-with-sonnet-enforcer	Enforces Sonnet model for Plan subagent to ensure thorough architectural reasoning	Guardrails
plan-with-opus-enforcer	Enforces Opus model for Plan subagent for maximum reasoning depth	Guardrails
redundant-read-blocker	Prevent wasteful re-reads of unchanged files with smart range tracking and context decay	Guardrails
codex-integration	Consult OpenAI Codex for fresh perspective — auto-escalation when stuck, on-demand second opinions, and web research	Development

View full README on GitHub

Stats

Version1.0.0

ReleasedJan 23, 2026

LanguageShell

Stars4

MaintenanceGood

LicenseMIT

Last CommitApr 14, 2026

AddedApr 2, 2026

Actions

View on GitHub View README Plugin Marketplace JSON

Available In

Tags

Categories

Keywords

behavior-analysis

Publisher marketplacebehavior-diagnostics@itb-ai-tools · marketplace and plugin share one repository (it-bens/ai-tools)

$

npx claudepluginhub it-bens/ai-tools --plugin behavior-diagnostics

More by it-bens

software-writer-extension-setup

9·

One-time setup skill that explores a project's codebase, drafts project-specific extension content conversationally, and writes the per-skill extension files for the software-writer plugin's writing-code, writing-tests, and writing-docs skills (delivery on Claude Code ships with software-writer 2.x; Codex delivery via AGENTS.override.md). Includes a re-sync mode that audits existing extension files for drift and migrates v1 hook-contexts setups. Long plugin and skill names are intentional to prevent accidental invocation.

3d

v2.0.1

it-bens

software-writer

9·

Three universal, opinionated skills for writing software: writing-code (API-consultation gate, dependency shape, stack footgun check, two-tier comment policy), writing-tests (classicist behavior-first workflow with stack-specific idioms), and writing-docs (single-owner surfaces, pointer-file discipline, anti-slop validation via the human-author:ai-slop-writing-fixer subagent). Each skill is extendable at every step via Pre-Step-N / Post-Step-N positions and via recognized named configuration values; the plugin ships hooks that deliver a project's extension files (.claude/extensions/software-writer/) wrapped in a structural envelope.

3d

v2.0.1

it-bens

subagent-orchestrator

9·

Orchestrate implementation and review work through dispatched workers — Codex CLI (GPT-5.6) and Claude subagents — with a task-strategy workflow, model routing, fenced write scopes, and independent two-worker verification

6d

v1.0.0

it-bens

plan-with-sonnet-enforcer

4·

Enforces Sonnet model for the Plan subagent. Ensures thorough architectural reasoning during plan mode.

3mo

v1.0.0

it-bens

commit-message-generator

4·

Generate and validate conventional commit messages from explicit git references. Features /commit-gen to create messages, /commit-check to validate format and consistency. Automatically detects commit type (feat/fix/refactor/etc.), infers scope from file paths, identifies breaking changes. Includes body validation (presence, content quality, migration instructions) and cross-platform clipboard integration. Supports project-specific configuration via .commitmsgrc.md including optional attribution footer. Comprehensive validation for type accuracy, scope matching, subject precision, and body quality.

3mo

v3.0.0

it-bens