Interrogator — Testing & QA agent for Claude Code
Fresh-context adversarial read of a spec: finds a compliant-but-wrong implementation, and reports blocking ambiguities a Drone would have to guess.
How to install Interrogator
Installs to ~/.claude/agents/quintinbotes-swarm-interrogator.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/QuintinBotes/swarm/HEAD/agents/interrogator.md -o ~/.claude/agents/quintinbotes-swarm-interrogator.md Restart Claude Code, or start a new session, for it to be picked up.
What Interrogator does
name: interrogator model: opus description: "Fresh-context adversarial read of a spec: finds a compliant-but-wrong implementation, and reports blocking ambiguities a Drone would have to guess" disallowedTools:
- Edit
- Write
- Agent
Interrogator Agent
You are the Interrogator — the **Changeling**. You read a spec exactly once, with no memory of the conversation that produced it, and you try to break it.
You exist because the session that drafted the spec cannot grade it honest
Alternatives in Testing & QA
- Test Wiring Auditor — 変更差分に対してテスト網が追随しているかを fresh-context で監査する read-only auditor 3.1k ★
- Test Gap Finder — Finds missing, weak, or stale test coverage in a diff 548 ★
- Weak Exercise — Minimal-context exercise agent for the weak-agent-test benchmark 234 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Spec Challenger
Adversarial reader of a draft spec, invoked by /architect before the GitHub issue is created. Starts with clea
Cyc Outsider Reviewer
Reviews one shipped artifact (manual, language spec, player instructions, README) as an outsider who has only
Fresh Eyes Reviewer
First-time reader perspective on a paper. Reads cold with no prior context — not the spec, not the lit review,
Fresh Verifier
Fresh-context Opus 5 verifier. Run after a builder reports done. Checks work against the spec, runs tests, rep
Premise Checker
Adversarially test one explicit consequential premise in fresh read-only context; return supported, revise, or
Suite Auditor
Audits an automated test suite and scores it against a rubric. Finds sleeps, duplication, missing assertions,
Related Skills
Dotnet QA
Story QA - multi-agent verification of a story implementation against its spec: per-AC verdicts, code reuse an
Da
Explicit Diablo invocation — adversarial critic for spec, plan, or implementation. Outputs FATAL/SERIOUS/SUSPI
Plan Dc
Turn a spec into a detailed implementation plan (the HOW), with ADR review and dual adversarial review — step