Debate Vs

Debate an opponent LLM on the best implementation approach using multi-turn conversations, then synthesize and implement.

Load the consult-llm skill before proceeding — it defines the invocation contract (stdin heredoc, flags, output format, multi-turn). Do not call the CLI without loading it first.

Available models

Selectors resolvable in this environment (depends on configured API keys):

!`consult-llm models`

Phase 0: Load consult-llm Skill

Load it now. Follow its invocation contract for all CLI calls in this workflow.

Configuration

Arguments: $ARGUMENTS

Check the arguments for flags:

Opponent flag (exactly one required): any --<selector> from the Models block above (e.g. --gemini, --openai, --deepseek). Translates to -m <selector> for the CLI.

Mode flags:

• --dry-run → debate and plan only, skip implementation
• --skip-final → skip the final review phase
• --rounds N → number of debate rounds (default: 1, max: 3). Each round = agent argues + opponent responds.

Strip all flags from arguments to get the task description.

Set variables from the opponent flag:

• MODEL: the selector (e.g. gemini, openai)
• OPPONENT: the same selector, used as the display label

If no --<selector> flag is provided, ask the user which opponent to use, listing the selectors from the Models block.

Phase 1: Understand the Task (No Questions)

1. Explore the codebase - use Glob, Grep, Read to understand:

   • Relevant files and their structure
   • Existing patterns and conventions
   • Dependencies and interfaces

   Before planning or consulting, do enough research to understand how the requested behavior actually works. Before starting, think about what resources would be useful to obtain first: relevant source files, tests, logs, generated files, config, examples, command output, external docs, or authoritative upstream source. Gather the cheapest useful evidence before forming a plan.

   Do not stop at the first plausible file, definition, setting, or example. Follow references, callers, related tests, and runtime usage until you can explain the current behavior and the likely impact of changing it.

2. Ground external semantics before planning - understand the requested behavior in the real system, not just this repo

   • If the task depends on an external product, CLI, API, protocol, file format, or ecosystem convention, verify the relevant behavior using the cheapest authoritative evidence available: local binaries/flags, generated files, official docs, public source, package/library code, or web search.
   • Capture only decision-relevant facts that affect scope, acceptance criteria, compatibility, or implementation constraints.
   • Do not create a separate research artifact unless the evidence materially changes the plan.

3. Make evidence-backed assumptions - do NOT ask clarifying questions

   • Use best judgment based on codebase and external context
   • Prefer simpler solutions when ambiguous
   • Follow existing patterns in the codebase

4. Prepare context summary - create a brief summary of:

   • The task to be implemented
   • Relevant files discovered
   • Key patterns and conventions in the codebase
   • Any constraints or considerations

Phase 2: Opening Arguments

Both debaters propose their approach independently.

Step 1: Agent's Opening Argument

You ARE the debater. Form your own implementation approach based on what you found in Phase 1. Write it out in full:

## Agent's Opening Argument

1. **Approach**: [2-3 sentences]
2. **Key decisions**: [architectural/design decisions]
3. **Files**: [files to create or modify]
4. **Steps**: [implementation steps]
5. **Trade-offs**: [pros and cons]

Present this to the user so they can see your position.

Step 2: Opponent's Opening Argument

Invoke consult-llm per the consult-llm skill with -m <MODEL> and -f <path> for each relevant source file discovered in Phase 1. Send the opening prompt below per the consult-llm invocation contract.

Opening prompt:

I need to implement the following task:

[Task description]

Here's what I found in the codebase:
[Context summary - relevant files, patterns, conventions]

Propose your implementation approach:
1. **Approach**: Describe your recommended approach in 2-3 sentences
2. **Key decisions**: List the main architectural/design decisions
3. **Files**: What files to create or modify
4. **Steps**: High-level implementation steps
5. **Trade-offs**: What are the pros and cons of this approach?

Be specific and opinionated. Defend your choices.

Save the returned thread_id for subsequent rounds (see consult-llm's multi-turn section).

Present the opponent's opening argument to the user as ## OPPONENT's Opening Argument.

Phase 3: Debate Rounds

For each round (default 1, configurable with --rounds N):