Skip to main content
TRW
TRWAgent Roles

Agents

A single agent holding an entire codebase in context misses things. Focused agents with narrow context windows catch what broad agents miss. TRW ships 12 bundled agents overall. In practice, most sprints revolve around a recommended five-role lineup, while the rest of the bundle covers explicit leadership, testing, traceability, and specialist requirement work.

Info

This page starts with the recommended sprint roster, then shows the additional bundled specialists that remain available when you want a more explicit team design.

Recommended day-to-day roster: five roles. That keeps most sprints understandable, but the shipped bundle is intentionally broader. Upgrading older playbooks? See migration map below.

How it works

Agent Teams follow a delegation model. The primary agent decomposes work, each specialist operates in isolation via worktrees, and structured messages replace shared state.

  1. 1

    Primary agent decomposes the work

    The orchestrating agent reads the sprint plan and PRD execution plans, then creates tasks with explicit file ownership boundaries for each specialist.

  2. 2

    Each agent gets only what it needs

    Implementers receive exclusive file sets in separate worktrees. No agent sees another's files. Narrow context means deeper understanding per task.

  3. 3

    Communication via structured messages

    Agents exchange interface contracts and completion signals through the task system. No shared mutable state, no merge conflicts.

  4. 4

    Auditor verifies integration

    Before delivery, trw-auditor checks that all agent outputs wire together correctly against the PRD acceptance criteria.

team activity
> /trw-sprint-team

[Primary] Reading sprint plan: sprint-79.yaml
[Primary] PRDs to implement: PRD-CORE-092, PRD-CORE-094
[Primary] Creating 3 teammate tasks with worktree isolation...

  Task 1: impl-092 → trw-implementer
    Files: src/agents/, data/agents/
    Contract: 5-agent roster, PREDECESSOR_MAP exported

  Task 2: audit-092 → trw-auditor
    Files: (read-only verification)
    Blocked by: Task 1

  Task 3: review-094 → trw-reviewer
    Files: (read-only review)
    Contract: rubric scores for all changed modules

[implementer] Task 1 complete. Build check: PASS (1337 tests, 94% coverage)
[auditor] Task 2 complete. All FRs verified. 0 spec gaps.
[reviewer] Task 3 complete. Rubric scores: correctness 9/10, security 10/10.
[Primary] Integration check: all contracts satisfied.
[Primary] Sprint delivered. 2 PRDs, 0 integration gaps.

Info

Model assignment: deeper creation roles such as trw-implementer and trw-prd-groomer default to Opus, most research and review roles default to Sonnet, and lightweight traceability or simplification helpers use Haiku. Model assignment is configurable per project.

Core sprint roster

These five roles cover most implementation sprints. Each one has a single mandate, a defined trigger condition, and worktree isolation for parallel work.

AgentRoleWhen to useModel
trw-implementerCode implementation specialist. Writes production code following TDD, honors interface contracts and file ownership boundaries.Writing production code, TDD, file ownershipOpus
trw-researcherResearch and investigation specialist. Explores codebases and the web, gathers evidence, produces structured findings.Codebase exploration, web research, evidence gatheringSonnet
trw-reviewerCode review and audit specialist. Read-only, rubric-scored reviews with security auditing.Rubric-scored reviews, security auditingSonnet
trw-auditorAdversarial spec-vs-code auditor. Verifies implementation against PRD acceptance criteria, checks type safety, DRY violations, and error handling.Spec compliance, type safety, DRY, error handlingSonnet
trw-prd-groomerPRD drafting and validation specialist. Grooms requirements to sprint-ready quality, manages the full PRD lifecycle.Requirements engineering, PRD lifecycleOpus

Additional bundled specialists

These agents are still part of the shipped inventory. Reach for them when you want explicit lead/test separation, lighter-weight utilities, or requirement work split into smaller responsibilities.

AgentRoleWhen to useModel
trw-leadExplicit team orchestrator for large multi-agent sprints and wave-based execution.When you want a dedicated lead coordinating teammatesOpus
trw-testerTesting specialist focused on PRD acceptance criteria and high diff coverage.When implementation and test authoring should be split across teammatesSonnet
trw-traceability-checkerCoverage verifier for bidirectional mapping between PRDs, code, and tests.Validate or deliver phases where traceability is the main questionHaiku
trw-code-simplifierTargeted cleanup helper that simplifies code without changing behavior.Post-implementation simplification passesHaiku
trw-adversarial-auditorDeeper spec-vs-code auditor used for more aggressive multi-wave verification.High-risk audits where an extra adversarial pass is worth the costSonnet
trw-requirement-writerFocused FR/NFR drafting helper for expanding or repairing a PRD.When requirement writing needs to be split from overall groomingSonnet
trw-requirement-reviewerStructured PRD reviewer that scores readiness without rewriting the document.Independent requirement review before sprint planningSonnet

Formation patterns

Three common team shapes. Pick the smallest formation that covers the work.

Solo + reviewer

Lead
Impl
Reviewer

One implementer does the work, an independent reviewer catches what they missed. Worktrees keep each agent isolated.

trw-implementertrw-reviewer

When: Most common. Single-PRD features, refactors, bug fixes that touch 3-10 files.

Parallel implementers

Lead
Impl-1
Impl-2

Each implementer gets exclusive file ownership. No shared state, no merge conflicts. The auditor verifies integration seams.

trw-implementer x2-3trw-auditor

When: Multi-package changes where files have no overlap. API + frontend, or two independent modules.

Full sprint team

Lead
Impl-1
Impl-2
Tester
Reviewer
ImplementerTesterReviewer

Full team with dedicated research, implementation, and review. Each role operates in its own worktree with exclusive file ownership.

trw-implementer x2trw-researchertrw-reviewertrw-auditor

When: PRD sprints delivering 2-4 PRDs in parallel. Quality-critical or security-sensitive work.

When to use agent teams

Agent teams add coordination overhead. Use them when the benefits outweigh the cost:

  • Multi-file features — changes span 3+ files across different modules or packages
  • Parallel PRDs — a sprint delivers 2+ PRDs that can be implemented concurrently
  • Quality-critical work — security hardening, API migrations, or anything that benefits from independent review
  • Large refactors — splitting a god module, migrating a dependency, or restructuring packages

Warning

When NOT to use teams: For single-file fixes, quick config changes, or edits touching fewer than 3 files, a solo agent session is faster. The coordination overhead of a team outweighs the benefit when there is nothing to parallelize.

Quality gates

Agent teams include automatic enforcement at every stage:

  • Teammates are blocked from completing tasks until trw_build_check passes
  • Idle agents with unfinished tasks get nudged automatically
  • trw-auditor verifies integration across all agent outputs before delivery
  • Each agent performs FR-by-FR self-review before marking work complete

Tip

Lifecycle hooks: TRW runs lifecycle hooks in the background — blocking agents who skip tests, warning on missed delivery, and preserving state before context compaction. Phase-change hook emissions were reduced from 20-100 per session to 3-5 in Sprint 79. These are automatic. No configuration needed.

Next steps

Agents make the most sense when you pair them with the requirements they should satisfy, the skills that invoke them, and the tool surface they act on while they work.

Next Step

Once you know the roles, use requirements and lifecycle guidance to decide what each agent owns and how work moves between them.