Coverage Auditor — Development agent for Claude Code
L0.96 Quality Gate — compares per-file Istanbul/c8 coverage against docs/metrics/coverage-baseline.json after every Vitest pass.
How to install Coverage Auditor
Installs to ~/.claude/agents/contact715-jidoka-coverage-auditor.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/contact715/jidoka/HEAD/.claude/agents/coverage-auditor.md -o ~/.claude/agents/contact715-jidoka-coverage-auditor.md Restart Claude Code, or start a new session, for it to be picked up.
What Coverage Auditor does
name: coverage-auditor description: L0.96 Quality Gate — compares per-file Istanbul/c8 coverage against docs/metrics/coverage-baseline.json after every Vitest pass. Blocks on any file dropping more than 5% coverage. Delegates delta math to scripts/coverage-delta.mjs. tools: Read, Bash, Grep, Write
Coverage Auditor
You are the Coverage Auditor for **this agentic framework**.
Role
L0.96 — Quality Gate layer. Runs in parallel with a11y-auditor and security-scanner, after test-runne
Alternatives in Development
- Dashclaw Gate Runner — Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the fa 297 ★
- Gsd Nyquist Auditor — Fills Nyquist validation gaps by generating tests and verifying coverage for phase requirements 62 ★
- Agents Docs — AGENTS.md — Documentation Math Notation (canonical & binding) 61 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Iteration Guard
The verify gate of the Logic-Lens iteration loop. Given a baseline iteration and a candidate iteration, compar
Unit Economist
Use when validating C3 (custo ≤ 25% do preço), reviewing baseline-cost.md, auditing recalc_unit_economics_requ
Eval Case Auditor
Read-only auditor for triage eval cases. Use after adding several cases or before promoting a baseline. Report
Baseline Auditor
Use this agent to judge whether a captured baseline is trustworthy before it gets frozen and committed for ver
Manual Rule Liveness Prober
Probes a manifest manual rule for liveness via with/without-rule fresh-subagent dispatch, capturing a RED→GREE
Specflow Quality Auditor
Quality and compliance auditor for SpecFlow artifacts. Use for ambiguity checks, coverage checks, checklist ve
Related Skills
Validate Benchmark
Benchmark validation coverage, speed, and evidence quality against baseline metrics
Guardrail
Guardrails for AI coding agents. A Claude Code plugin that blocks or asks before risky actions (dropping table
Coverage Guard
An AI agent skill that enforces 100% test coverage for any JavaScript/TypeScript project. Works with Vitest, J