Ndv Signal — Testing & QA agent for Claude Code
Metrics skeptic.
How to install Ndv Signal
Installs to ~/.claude/agents/emb715-neurodiveragents-ndv-signal.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/emb715/neurodiveragents/HEAD/agents/ndv-signal.md -o ~/.claude/agents/emb715-neurodiveragents-ndv-signal.md Restart Claude Code, or start a new session, for it to be picked up.
What Ndv Signal does
name: ndv-signal model: claude-sonnet-4-6 effort: high description: Metrics skeptic. Use when reviewing engineering KPIs, OKRs, sprint velocity, test coverage targets, DORA metrics, or any measurement system. Audits whether metrics measure what they claim to measure. Goodhart's Law as a cognitive style — the moment a measure becomes a target, it stops being a measure, and Signal notices before anyone else does. tools:
- Read
- Grep
- Glob
- Bash
You are **Signal**. Pattern recog
Alternatives in Testing & QA
- Witness — Independently witness that an Allium loop's convergence claim is true and was reached honestly 474 ★
- Checklist Generator — Use when an orchestrator needs to enumerate every verifiable claim in a code diff (dependency interactions, te 115 ★
- Minions QA — QA — test scenario generation from user stories and PRDs, web application testing guidance, quality gate revie 52 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Spec Reviewer Correctness
Review an engineering spec for correctness — does the proposed implementation actually solve the problem the b
Fullstack QA Debugger
QA and debugging agent for fullstack applications. Use to validate API connections, test error states, measure
Analytics Interpreter
Marketing data analyst for attribution modeling, dashboard design, reporting, A/B test analysis, and marketing
Learning Designer
Use to produce or revise the pedagogical spec (SPEC.md) and all user-facing copy (copy.json) for the Monty Hal
Test QA
Regression-focused verifier for contracts, error paths, and high-signal tests.
Log Digger
Triage high-volume output — cloud logs, container logs, test suite runs, build failures, long SQL result sets
Related Skills
Measure
Metrics plan — HEART framework, OKRs, experimentation strategy, dashboards, and baseline measurement.
Uisight
Your AI can already see the screen — it just can't measure it. Live mobile+desktop sessions, a measurement eng
Productivity Report
Generate a SPACE-framework productivity report with DC velocity, DORA metrics, LOC churn, and longitudinal com