Worker Sonnet — Testing & QA agent for Claude Code
Tier-2 worker on Sonnet.
How to install Worker Sonnet
Installs to ~/.claude/agents/drmanojkurmana-synergy-worker-sonnet.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/drmanojkurmana/synergy/HEAD/agents/worker-sonnet.md -o ~/.claude/agents/drmanojkurmana-synergy-worker-sonnet.md Restart Claude Code, or start a new session, for it to be picked up.
What Worker Sonnet does
name: worker-sonnet description: Tier-2 worker on Sonnet. Use for well-specified, bounded work - implementing a decided design, writing tests, mechanical refactors, search sweeps, log trawls, doc updates. Give it a spec, not an open question. model: sonnet
You are a tier-2 worker in a fleet led by a Claude Code session.
- The task is expected to be well specified. If it is not, say what is missing instead of guessing at scope.
- Match the surrounding code's style. Reuse what is already
Alternatives in Testing & QA
- Prod Incident Responder — Reads recent prod logs, picks the highest-impact recurring error, drafts a minimal fix PR with a regression te 324 ★
- Claude Code Test Agent — Tests all 27 Claude Code hooks by logging each event to tests-agents-hook/agent-hook-fired.log 321 ★
- Writ Implementer — Implements all files listed in an approved plan 187 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Sonnet Implementer
Mid-size implementation work delegated per the company model — feature slices, refactors within a defined scop
Fast Worker
Mechanical, low-risk bulk work, mechanical edits, inventory sweeps, repetitive migrations, generated-file main
Build Leg
Bounded Opus build leg for mechanical labor against a ruled spec — fixtures, mechanical variations on an exemp
Router Sonnet
Worker subagent dispatched by the auto-model-router for standard development tasks — routine refactors, doc an
Grays Run
Mechanical test runner (Haiku tier). Auto-detects pytest, jest, vitest, playwright. Runs tests, reports pass/f
Forge Standard
forge plan-execution worker for standard-tier tasks — well-specified changes with a clear test path — and for
Related Skills
V Triage
Classify one change request before any work starts — resolve, score, and write plus COMMIT the pre-eval triage
Agent Skills Discovery RFC
A mechanism for discovering Agent Skills using the .well-known URI path prefix as specified in RFC 8615 for di
Fleet Lane Dispatch
Use when dispatching a batch of autonomous CCC worker lanes with a mission brief and a report_to return addres