Generator Agent — Testing & QA agent for Claude Code
Drafts CFO artifacts while tagging every displayed number for independent QA.
How to install Generator Agent
Installs to ~/.claude/agents/mlobo2012-round-finance-agents-generator-agent.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/mlobo2012/round-finance-agents/HEAD/agents/generator-agent.md -o ~/.claude/agents/mlobo2012-round-finance-agents-generator-agent.md Restart Claude Code, or start a new session, for it to be picked up.
What Generator Agent does
name: generator-agent description: Drafts CFO artifacts while tagging every displayed number for independent QA. tools: Read, Grep, Glob
Generator Agent
You create draft CFO outputs. You do not certify numbers, publish final artifacts, or hide unresolved evidence.
Inputs
contract.jsonsource_ledger.json- workflow template
- source summaries or extracts supplied by the main session
- prior
revision_log.mdentries
Outputs
generator_output.mdor draft content fo
Alternatives in Testing & QA
- Ad Onboard Reviewer — Independent reviewer for AutoDeploy model onboarding 14.5k ★
- Integration Test Generator — Generates one integration/E2E test from an approved test case spec using existing project patterns 548 ★
- Prod Incident Responder — Reads recent prod logs, picks the highest-impact recurring error, drafts a minimal fix PR with a regression te 324 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Numerical QA Agent
Independently recomputes every displayed number and writes fail-closed numerical QA evidence.
Mutation Survivor Triage
Classifies mutmut survivors and produces a per-file action list. Use after uv run mutmut run when survivors 0,
Wasp Refactor Executor
Execute mechanical refactorings (DRY, extract function, rename) while maintaining test green status. Optimized
Narrative Evaluator Agent
Reviews CFO narrative for support, audience fit, and unsupported claims after numerical QA.
Resource Manager
Use BEFORE dispatching any TEST-RUNNING subagent (a builder, a fix-subagent, qa-engineer) to get a GO/HOLD ver
Eval Author
Authoring role for the D365FO agent eval loop catalog. Drafts a new eval/cases/ .json spec (valid against eval
Related Skills
Claude Council Of Five
Claude Code skill: five personas (Chair, Devil's Advocate, Principles Purist, Outsider, Executor) debate your
PolyClaw
PolyClaw is a vendor-independent fork of Claude Code. While the original tool locks terminal agentics into a s
Resume Consultant Harness
Tailored-resume Claude Code skill using Planner → Generator → Evaluator harness with Zero AI Slop policy and i