crouton-labs

crouton-labs/crouton-kit

Plugin Claude Code

Personal Claude Code plugins for development workflows.

crouton-labs/crouton-kit

Instructions file

Claude Code instructions for crouton-labs/crouton-kit, covering claude.md, architecture, key constraints, commands and build ai-cli (run from plugins/ai-cli/).

crouton-labs/crouton-kit

Skill Claude CodeCodex

This is an example skill, showcasing forked contexts. With forked context, the agent will execute in a fresh context, using the system prompt of the agent. It will pass the skill as context, along with arguments at the end, or replacing $ARGUMENTS with the arguments passed when the skill is called.

crouton-labs/crouton-kit

Plugin Claude Code

CLI tool for running Claude Code SDK sessions with configurable modes.

crouton-labs/crouton-kit

Skill Claude CodeCodex

Guide to writing ai-cli mode files. Use when creating modes for non-interactive Claude Code sessions — preconfigured agent runs with locked-in system prompts, model selection, and prompt wrappers.

crouton-labs/crouton-kit

Plugin Claude Code

Multi-step agent workflows — chain headless ai-cli runs with branching and Linear integration.

crouton-labs/crouton-kit

Command

Run or inspect ai-workflow automated pipelines.

crouton-labs/crouton-kit

Hook

Runs when the agent finishes a response, executing require-submit.py. From crouton-labs/crouton-kit.

crouton-labs/crouton-kit

Plugin Claude Code

Guides for authoring Claude Code artifacts — CLAUDE.md files, hooks, rules, skills, commands, and scripts.

crouton-labs/crouton-kit

Skill Claude CodeCodex

Best practices for writing effective CLAUDE.md files. Use when creating, updating, or auditing CLAUDE.md files for projects or directories.

crouton-labs/crouton-kit

Skill Claude CodeCodex

Design CLIs for humans and LLM agents — subcommand shape, output streams, exit codes, JSON modes, TTY-aware color, structured errors, mutation safety. Use when building or refactoring a CLI, adding machine-readable output, writing --help, deciding stdout vs stderr, or making a tool agent-friendly.

crouton-labs/crouton-kit

Skill Claude CodeCodex

Guide to writing slash commands for Claude Code. Use when creating commands that set mode, constraints, or workflows invoked via /command-name.

crouton-labs/crouton-kit

Skill Claude CodeCodex

Token budgeting, placement effects, RAG patterns, prompt caching, compression, and multi-turn context strategies for LLM applications. Use when dealing with context windows, token budgets, retrieval-augmented generation, long context, context overflow, caching costs, observation masking, or compressing LLM inputs.

crouton-labs/crouton-kit

Skill Claude CodeCodex

Evaluation strategies and quality gates for LLM systems. LLM-as-judge implementation, prompt regression testing, structural and semantic validation pipelines, production monitoring, guardrails, and metrics that actually work. Use when building evals, setting up CI quality gates, testing prompts, measuring output…

crouton-labs/crouton-kit

Skill Claude CodeCodex

Guide to Claude Code hooks — lifecycle events, handler types, decision control, and common patterns. Use when creating, debugging, or planning hooks for guardrails, context injection, quality gates, notifications, or automation.

crouton-labs/crouton-kit

Skill Claude CodeCodex

Design and implement multi-agent LLM systems. Covers orchestrator patterns, parallel agent coordination, pipeline architecture, hierarchical delegation, agent communication, and failure handling. Use when building multi-agent workflows, coordinating parallel agents, designing orchestrators, splitting tasks across…

crouton-labs/crouton-kit

Skill Claude CodeCodex

Techniques for getting varied, non-repetitive outputs from repeated LLM calls. Use when building systems that call LLMs in loops, generating personality lines, commentary, names, or any repeated creative text where outputs feel samey or cliche.

crouton-labs/crouton-kit

Skill Claude CodeCodex

Structure Claude prompts for clarity and better results using roles, explicit instructions, context, positive framing, and strategic organization. Use when crafting prompts for complex tasks, long documents, tool workflows, or code generation.

crouton-labs/crouton-kit

Skill Claude CodeCodex

Guide to writing .claude/rules/.md files — auto-applied constraints scoped by file patterns. Use when creating or updating rules for code conventions, quality standards, or file-specific guidance.

crouton-labs/crouton-kit

Skill Claude CodeCodex

Guide to creating CLI tools and scripts that augment Claude Code. Use when building bin/ executables, automation scripts, hook handlers, or tooling that abstracts repeated agent workflows.

crouton-labs/crouton-kit

Skill Claude CodeCodex

Guide to writing SKILL.md files for Claude Code. Use when creating skills that provide on-demand reference, methodology, or workflow guidance.

crouton-labs/crouton-kit

Skill Claude CodeCodex

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…

crouton-labs/crouton-kit

Skill Claude CodeCodex

Get reliable typed JSON from LLMs using constrained decoding, JSON Schema, Zod, Pydantic, and Instructor. Use when implementing structured output, JSON schema validation, typed API responses, constrained generation, Zod schemas, Pydantic models, schema design for LLM extraction, streaming structured data, or debugging…

crouton-labs/crouton-kit

Skill Claude CodeCodex

What belongs in system prompt vs user prompt and why. Placement decisions for API calls, system messages, and prompt architecture — system as identity/constraints/tools, user as task/context/state. Use when designing system prompts, structuring API calls, deciding where instructions belong, writing prompts for…