git:20261017.35b5927 to git:20261018.a370713

55 added, 30 removed. Audit A to A.

---

name: code-review

- description: Multi-agent code review with parallel specialized reviewers, architecture validation, challenge validation, and durable handling of previously decided findings. Use `rq` to request a review of diffs (defaults to main branch), `rs` to respond to findings and record intentional non-fix decisions beside the relevant code. Triggers on "review this", "review my code", "code review", "check for bugs", "audit this", when examining PRs, pull requests, branches, or diffs. Always asks user before applying fixes or adding decision comments.

+ description: Multi-agent code review run as a debate. Critics raise findings in parallel, an Author defends the change, Critics concede or maintain, and a Judge rules on what stays contested. Findings are classified by kind and blocking, and handled durably when previously decided. Use `rq` to request a review of diffs (defaults to main branch), `rs` to respond to findings and record intentional non-fix decisions beside the relevant code. Triggers on "review this", "review my code", "code review", "check for bugs", "audit this", when examining PRs, pull requests, branches, or diffs. Always asks user before applying fixes or adding decision comments.

argument-hint: "rq [branch] | rs"

user-invocable: true

---

# Code Review Skill

- Multi-agent code analysis with a simplicity gate, focused reviewers, and challenge validation.

+ 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](../../docs/research/multi-agent-debate.md).

Uses explicit subagent dispatch patterns from [code-subagents](../code-subagents/SKILL.md).

## 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, but never name a specific agent. The harness chooses the

- available agent whose description best fits the step's task. Steps and the kind of work they

- need:

+ 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, reviewer selection |

- | Reviewers | Critical analysis: evidence-based critique and failure-mode analysis |

- | Architect | Architecture, design-boundary, data-model, and API-contract review |

- | Challenge | Critical analysis: validate or reject findings |

+ | 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 |

- Reviewer names such as `Security`, `Correctness`, `Maintainability`, and `PerformanceOperator` are prompt personas, not agent types.

+ 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 reviewer persona on every review. For migrations, refactors, and

- architectural changes it is a gate: run it before the other reviewers. Otherwise it runs in

- parallel with them. It runs once and is never listed in triage's `reviewers`.

+ `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.

- ### rq (Request Review) Subagents

+ ## Finding Classification

- | Step | Parallel | Purpose |

- |------|----------|---------|

- | 1. Triage | No | Detect context, select reviewers, identify relevant skills to look for |

- | 2. Reviewers | Yes (per reviewer) | Simplicity (gate first for migrations, refactors, and architectural changes; otherwise in parallel), correctness, security, and other specialty analysis |

- | 3. Synthesis | No | Deduplicate findings inline |

- | 4. Architect | No | Architecture review |

- | 5. SDD + Challenge | No | Check SDD compliance last, then validate findings |

+ 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](./references/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](./references/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](./references/rs.md).

## Dispatch Patterns

Follows [code-subagents](../code-subagents/SKILL.md) patterns:

- - **Parallel dispatch** for independent reviewers

+ - **Parallel dispatch** for independent Critics and for Rebuttals

- **Sequential dispatch** for dependent steps

- - **Fresh subagent per task** — no context pollution

- - **Relevant skill search pre-step** before each analysis phase

- - **Error handling**: Log failures, continue with partial results

+ - **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

- Every step except synthesis and output uses a harness-selected agent (see Agent Selection).

- Synthesis is performed inline by the main agent.

+ 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](./references/rq.md) | Request review workflow - detailed steps with prompts |

+ | [rq.md](./references/rq.md) | Request review orchestration (main agent) |

+ | [roles/triage.md](./references/roles/triage.md) | Triage prompt template |

+ | [roles/critic.md](./references/roles/critic.md) | Critique and Rebuttal prompt templates |

+ | [roles/author.md](./references/roles/author.md) | Defense prompt template |

+ | [roles/judge.md](./references/roles/judge.md) | Ruling prompt template |

+ | [personas.md](./references/personas.md) | Persona catalog (focus areas, impact lens, skills to load) |

| [rs.md](./references/rs.md) | Respond to review workflow - interview mode |

- | [reviewers.md](./references/reviewers.md) | Dispatch template and reviewer definitions (single source for prompts) |

| [output.md](./references/output.md) | Output format specification |

## Workflow Routing

- No arguments, `rq`, or bare branch → [rq.md](./references/rq.md)

- `rs` → [rs.md](./references/rs.md)