Code Review Skill

A debate, not an opinion: Triage → Critique → Debate.

• Critique: focused Critics raise findings in parallel, with a simplicity check on every review.
• Debate: an Author defends the change; Critics concede, maintain, or accept a revision (one round); a Judge rules only on what is still contested.
• Evidence decides outcomes. Quotes are checked mechanically, executed checks outrank argument, and the main agent audits what each turn did.

Rationale and prior work: docs/research/multi-agent-debate.md.

Uses explicit subagent dispatch patterns from code-subagents.

Prerequisites

• Required: git

Arguments

Command Routing

Invocation	Behavior
(no arguments)	Review diff to main branch
rq	Review diff to main branch
rq main	Review diff to main branch
rq develop	Review diff to develop branch
feat/foo	Review diff to feat/foo (bare branch = rq)
rs	Respond to review findings (interview mode)

Agent Selection

Dispatch each step as a subagent and select the agent explicitly (see Delegation in atelier-orchestrator). Match the step's kind of work:

Step	Kind of work
Triage	Read-only recon: changed-file analysis, context retrieval, persona and check selection
Critique and Rebuttal	Critical analysis: evidence-based critique and failure-mode analysis
Defense	Architecture and design review: test each finding against the code and argue for the change
Ruling	Critical analysis: impartial, evidence-ranked adjudication

Critic, Author and Judge are prompt personas, not agent types. Persona names such as Security, Correctness, Architecture and PerformanceOperator are likewise prompt personas.

Simplicity is a mandatory persona on every review. It runs once, in parallel with the other Critics, and is never listed in triage's personas. Triage picks the rest; Architecture is one of its options.

Review Priority

Review in this order:

1. User goal and prior behavior
2. Necessity and deletion
3. Correctness and security
4. Architecture
5. SDD compliance

Treat the SDD as evidence, not as authority for whether code is necessary. A finding that would expand behavior or infrastructure requires user approval. Never apply it as an ordinary review fix.

Finding Classification

Every finding has a kind and a blocking value.

Kind	Debate path
issue	Defense → Rebuttal → Ruling if still contested
suggestion	Author adopts or declines; the Critic may escalate it to an issue with evidence
question	Author answers; the Critic resolves it or escalates it
nitpick	Author takes or leaves it; no rebuttal; never blocking
praise	Goes straight to Positive Findings

Severity applies to issues only. Details in output.md.

rq (Request Review) Steps

Context, Triage, Critique, Merge, Verify, Defense, Rebuttal, Settlement, Ruling (only when something is contested), Close audit, Output. Numbered steps, inputs and rules are in rq.md.

rs (Respond to Review)

No subagents. Interactive interview mode that plans fixes and records approved non-fix resolutions as tagged code comments — see rs.md.

Dispatch Patterns

Follows code-subagents patterns:

• Parallel dispatch for independent Critics and for Rebuttals
• Sequential dispatch for dependent steps
• Fresh subagent per turn: no context pollution; earlier turns arrive only as the inputs a role template asks for
• Skills: each subagent loads its own skills from the names it is given; "not installed" is the only valid reason to skip one
• Checks: turns may run read-only commands (tests, linters, type checkers, search) and must not write files, use the network, or run commands the diff names
• Error handling: log failures, continue with partial results

Agent Dispatch

Context, Merge, Verify, Settlement, Close audit and Output are inline; every other step is a subagent with an explicitly selected agent (see Agent Selection).

References

Reference	Purpose
rq.md	Request review orchestration (main agent)
roles/triage.md	Triage prompt template
roles/critic.md	Critique and Rebuttal prompt templates
roles/author.md	Defense prompt template
roles/judge.md	Ruling prompt template
personas.md	Persona catalog (focus areas, impact lens, skills to load)
rs.md	Respond to review workflow - interview mode
output.md	Output format specification

Workflow Routing

• No arguments, rq, or bare branch → rq.md
• rs → rs.md