Clive — Testing & QA agent for Claude Code
Use to heal failing tests CI reported.
How to install Clive
Installs to ~/.claude/agents/saimskywalker-warriors-of-light-ai-agents-clive.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/saimskywalker/warriors-of-light-ai-agents/HEAD/agents/clive.md -o ~/.claude/agents/saimskywalker-warriors-of-light-ai-agents-clive.md Restart Claude Code, or start a new session, for it to be picked up.
What Clive does
name: clive description: "Use to heal failing tests CI reported. Classifies each as isolation artefact, stale expectation or real bug and fixes the right side. Never deletes, skips or loosens a test." model: sonnet tools: Read, Grep, Glob, Bash, Edit, Write
You rise from the ashes: red tests become green the honest way.
For each failing test (from lightning's list):
- Run that file alone through the Slow queue. Green alone, red in the suite = ISOLATION (shared state, timers, fake a
Alternatives in Testing & QA
- Review Test Structure — Reviews test code for isolation, independence, readability, documentation quality, and proper setup/teardown 432 ★
- Codex Debugger — Root-cause a failing test, crash, stack trace, or misbehaving feature by delegating the investigation to OpenA 249 ★
- iOS Principal Engineer — Use this agent for ANY iOS code-related task in MacMagazine — feature implementation, bug fixes, architecture 169 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Sdlc Bug Investigator
Diagnoses the root cause of a reported bug and writes exactly one failing RED test that reproduces it — never
Spec Runner
Runs the Savi specs affected by the current change and triages every failure into real-bug / stale-spec / pre-
Parallel Hunt Finder
Finder for a /parallel-hunt round — investigates the live system for real defects, writes evidence and a faili
TDD Test Writer
Writes failing tests for a ledger item. NEVER writes production code. Reads the spec, writes the test, runs it
TDD Engineer
Structured TDD engineer. Given a feature spec or bug report, writes a failing test first, confirms it fails fo
E2e Writer
Writes Playwright/Maestro e2e specs and classifies failing runs. Runs ONLY against the test environment; never
Related Skills
Om Tidy
Self-maintenance pass — acts on every hygiene flag: archives completed work, groups loose clusters, splits ove
Heal
Pull the Auto-Healer bug web for the current repo (or all repos) — recurrences, stuck bandaid-risk bugs, and t
Overnight PRs
Autonomous overnight loop — verify issues against the codebase, close stale ones, ship PRs through /ship (bug