By jobrien127
Procedural full-stack solution framework — math-grounded pipeline from problem to application
npx claudepluginhub jobrien127/plugin-marketplace --plugin solution-engineFeedback processing agent. Ingests outcome data, runs Bayesian weight updates, checks surrogate ladder correlations, and suggests parameter changes. Use when /calibrate is invoked.
Conversational agent for problem state collection. Walks users through the three-layer problem schema, detects gaps, suggests defaults, and produces problem-state.yaml. Use when /collect is invoked.
Sub-problem decomposition agent. Breaks the objective into classified sub-problems with execution order and algorithm candidates. Use when /decompose is invoked.
Math formalization agent. Converts problem-state.yaml into rigorous modular math specs with falsifiable assumptions, surrogate ladders, and Bayesian learning specs. Use when /formalize is invoked.
Code scaffolding agent. Produces application code stubs, test scaffolds, data schemas, and infrastructure config from component specs. Use when /generate is invoked.
Full-stack evaluation agent. Selects algorithms per sub-problem from the catalog and evaluates technology candidates per application layer. Use when /select is invoked.
Implementation spec writer. Generates per-component specs from math formalization and stack selection. Covers all application layers including experience and market. Use when /specify is invoked.
Test and simulation agent. Runs scaffold build checks, unit tests, math verification, and simulation scripts. Produces test report. Use when /validate is invoked.
Feed outcome data back into the model. Updates quality weights, engagement parameters, and optionally skill/agent prompts.
Reload pipeline state and continue from where the last session left off
Guided problem state collection across all three layers (optimization, market-making, experience)
Decompose objective into sub-problems with complexity classification and execution order
Convert problem state into rigorous math modules with falsifiable assumptions and surrogate ladder
Scaffold application code from specs across all application layers
Evaluate algorithms and full-stack technology options per sub-problem and application layer
Generate per-component implementation specs from formalization and stack selection
Run test suites and simulations at every layer to verify the scaffold and math
Scored tradeoff tables and evaluation output with no narrative padding
Terse, LaTeX-aware output for math formalization work
Operational output — costs, infrastructure, alerts, runbooks, pipeline status
Structured specification output with typed fields, tables, and interface definitions
Test results and validation output — pass/fail tables, coverage, simulation results
A local marketplace of Claude Code plugins — self-contained packages that extend Claude with hooks, skills, agents, and MCP servers.
v1.4.1Meta-plugin that injects project state into every session and synthesizes session transcripts into a persistent knowledge base. The backbone for self-improving Claude Code setups.
Skills: /whetstone:route, /whetstone:think, /whetstone:verify, /whetstone:compress, /whetstone:synthesizer, /whetstone:improve, /whetstone:setup
Auto-behaviors:
v0.1.0Routes tasks to the appropriate Claude model tier (Haiku / Sonnet / Opus) based on task complexity, reducing cost without sacrificing quality.
Skills: /dispatch:route, /dispatch:haiku, /dispatch:sonnet, /dispatch:opus
Interactive wizard for managing project-level settings.local.json permissions. Detects project type, suggests safe permission patterns, and reduces manual approval friction.
Command: /permissions
Features: Smart project-type detection, categorized permission safety levels, proactive suggestions when starting new projects.
Transparently converts structured data in prompts to TOON format for token-efficient LLM processing, then converts responses back to JSON for display. Saves 30–60% tokens on structured data.
Extraction methods: LLM (Claude API), Markdown tables, key-value regex — with graceful fallback.
v0.1.0MCP server and hook-driven automation for structured problem-solving workflows. Decomposes problems, specifies requirements, generates solutions, validates output, and resumes context across sessions.
Agents: decomposer, specifier, generator, validator, calibrator
Hooks: SessionStart (resume context), PostToolUse (validate stage), PreCompact/PostCompact (save/restore state)
Requires: Python ≥ 3.12, uv
v0.1.0Automated wiki maintenance for this plugin marketplace. Ingests plugin source files, lints wiki docs, and keeps the knowledge base in sync.
Agents: ingest-agent, lint-agent, remediate-agent, obsidian-agent
Each plugin is self-contained. Install by pointing Claude Code at the plugin directory:
# Load a single plugin
claude --plugin-dir /path/to/plugin-marketplace/whetstone
# Or copy to your Claude plugins directory
cp -r whetstone ~/.claude/plugins/
Then enable in ~/.claude/settings.json:
{
"enabledPlugins": {
"whetstone": true
}
}
Each plugin follows the Claude Code plugin spec:
<plugin-name>/
├── .claude-plugin/
│ └── plugin.json # Manifest: name, version, description, hooks
├── skills/ # Slash commands (/plugin:skill)
├── agents/ # Subagent prompt definitions
├── hooks/ # Lifecycle hook scripts
├── commands/ # Top-level slash commands
└── README.md
MIT
Persistent memory system for Claude Code - seamlessly preserve context across sessions
Admin access level
Server config contains admin-level keywords
Modifies files
Hook triggers on file write and edit operations
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Intelligent prompt optimization using skill-based architecture. Enriches vague prompts with research-based clarifying questions before Claude Code executes them
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Streamline people operations — recruiting, onboarding, performance reviews, compensation analysis, and policy guidance. Maintain compliance and keep your team running smoothly.