crouton-labs

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.

Pause agent execution to have the human validate decisions, choose between options, answer freetext, or comment on a document — via the `hl` CLI. Every interaction is a kickoff that returns a job handle immediately; collect the human's answer later with `hl job result`. Use for material design decisions, approval gates, picks between meaningful alternatives, and markdown doc review. Not for trivial yes/no confirmations the agent should decide itself.

Validate technical designs against requirements for coverage, feasibility, and architectural soundness. Use after creating a design.

Validate implementation plans against requirements and design. Use after creating a plan to ensure full coverage and no ambiguities.

Validate requirements documents for EARS compliance, completeness, and consistency. Use after creating requirements.

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.

Systematic debugging methodologies for hard bugs. Covers rubber ducking, code tracing, hypothesis testing, logging strategies. Use when stuck on bugs that resist quick fixes.

Test writing and fixing methodology. Covers TDD, investigating failures, and delegating fixes to agents. Use when writing tests or diagnosing test failures.

Forensic debugging of a past sisyphus multi-agent session — reconstruct what the orchestrator and each agent could see at each decision point and judge whether their calls were reasonable. Use when asked to debug, autopsy, or explain a sisyphus session: a failure, wasted cycles, a weird decision, a stalled agent, or how a session succeeded. Takes a session ID/name or a path to a session dir or exported dump.

Author new sisyphus agents, sub-agents, hooks, skills, and orchestrator modes. Use when extending sisyphus runtime behavior — adding a domain-specific agent variant, project-level hook, custom orchestrator phase, or shared skill. Covers what to put in each file, why, and which extension to reach for.

Project-local operational knowledge for THIS app, accumulated by prior operator runs. Covers app surfaces (routes, ports, processes, admin overlays), auth/login flow, db state management, common UI flows, and known footguns. Use whenever the operator agent needs project-specific operating knowledge — read at session start, update before submitting.

Runtime mental model, agent boundaries, and workflow patterns for the sisyphus multi-agent orchestration system

Browser automation and UI measurement through capture's session, page, tab, measure, motion, cdp, and lib branches. Use when observing a web app, driving its UI, collecting network evidence, or measuring rendered state over CDP.