G Forge Dev — Testing & QA agent for Claude Code
Use proactively to run this repo's test suites and g-dev/ gate fixtures and return attested runner output.
How to install G Forge Dev
Installs to ~/.claude/agents/onlygian-g-forge-g-forge-dev.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/onlygian/G-Forge/HEAD/.claude/agents/g-forge-dev.md -o ~/.claude/agents/onlygian-g-forge-g-forge-dev.md Restart Claude Code, or start a new session, for it to be picked up.
What G Forge Dev does
name: g-forge-dev description: Use proactively to run this repo's test suites and g-dev/ gate fixtures and return attested runner output. The execution counterpart to test-writer, which has no execution tool and cannot run anything — g-forge-dev closes that gap for THIS repo's own dogfooded plugin code only. model: haiku tools: Read, Glob, Grep, Bash, Write color: green
You run G-Forge's own test suites and `g-dev/` gate fixtures and report VERBATIM runner output. You are repo-local, de
Alternatives in Testing & QA
- Checklist Generator — Use when an orchestrator needs to enumerate every verifiable claim in a code diff (dependency interactions, te 115 ★
- Unit Test Writer — PHPUnit test writer for WordPress/WooCommerce PHP code 80 ★
- Test Runner — Run tests. Validate fixes 80 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Gql Runner
GQL validation runner. Runs all GraphQL queries from the web client and test suites against the dev API and lo
Runner
Test-suite execution on Opus 5. Use to run pytest, vitest, or the e2e suite and get back a digest of failures
Halmos Verification
Converts structured invariant specifications into compilable Halmos symbolic test suites (.t.sol) that run ins
Test Fixtures For Consistent Test Data
@pytest.fixture def valid_user(): return User( id="test-123", email="test@example.com", name="Test User", crea
Log Digger
Triage high-volume output — cloud logs, container logs, test suite runs, build failures, long SQL result sets
Harness Test Writer
Writes the acceptance tests for an approved /harness plan before any implementation, so the implementers have
Related Skills
Coding Agent Harness
Nodaris AI's harness for coding agents. It plans before it edits, proves its work before it says done, keeps s
Claude Editor Hook
Command palette for Claude Code via Ctrl-G hook. Spawn parallel Claude instances, stream logs, run tools - any
Claude Task Runner
by grahama1970 - A specialized tool to manage context isolation and focused task execution with Claude Code, s