Wh Fixer — Testing & QA agent for Claude Code
Verify and review-phase agent.
How to install Wh Fixer
Installs to ~/.claude/agents/muhibm1-workhorse-snapshot-wh-fixer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/muhibm1/workhorse-snapshot/HEAD/agents/wh-fixer.md -o ~/.claude/agents/muhibm1-workhorse-snapshot-wh-fixer.md Restart Claude Code, or start a new session, for it to be picked up.
What Wh Fixer does
name: wh-fixer description: Verify and review-phase agent. In verify mode fixes the specific failures the verifier reported, changing implementation code only while the test-lock hook is active; in review mode, run with the lock off, fixes every high or medium reviewer finding that came with a concrete fix, in implementation or in a test the finding names, never editing a test to make a failing implementation pass. Use with a failure list from verification.md or a findings list from reviews/
Alternatives in Testing & QA
- Claude Code Test Agent — Tests all 27 Claude Code hooks by logging each event to tests-agents-hook/agent-hook-fired.log 321 ★
- Al Spec Agent — Turn an approved Business Central requirement and architecture into one implementable AL specification 109 ★
- Auto Error Resolver — Fix compilation errors, build failures, type errors, or test failures 96 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Kotlin Test Fixer
Kotlin-only. Runs Kotlin/Kotest tests at module level, diagnoses failures, and fixes mismatches between servic
QA Fixer
Bounded test-fix loop agent for beast. Diagnoses test failures and applies targeted fixes, max 5 cycles.
API Test Fixer
Fixes API endpoint test failures, HTTP client issues, and API contract validation problems. Expert in REST API
Database Test Fixer
Fixes database mock client issues, database fixture failures, stored procedure/function mocks, computed column
Bnb Fixer
Corrective agent that fixes blocker-severity failures identified by Validator. Runs at end-of-run fix pass or
Task Builder
Implement a frozen task spec and later package evidence without changing production code during evidence mode
Related Skills
Cmd Judge
Adversarial verifier for the PROVE phase: treats a finished-work report as untrusted claims, re-runs every ver
Bake
Implement one milestone (or all sequentially with checkpoints) from the active run's milestones/. Spawns Baker
Refactor Safe
Refactor internals without changing public API. Fixes structural problems (long functions, duplication, poor n