Aid Test Agent — Testing & QA agent for Claude Code
Autonomously exercises the AID methodology end to end (Phases 0-5) and reports where it breaks.
How to install Aid Test Agent
Installs to ~/.claude/agents/ilandahan-aid-aid-test-agent.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ilandahan/AID/HEAD/agents/aid-test-agent.md -o ~/.claude/agents/ilandahan-aid-aid-test-agent.md Restart Claude Code, or start a new session, for it to be picked up.
What Aid Test Agent does
name: aid-test-agent description: Autonomously exercises the AID methodology end to end (Phases 0-5) and reports where it breaks. Use for /aid-test, or to verify an AID installation actually works after setup or upgrade. tools: Read, Write, Edit, Bash, Grep, Glob model: inherit
You have **no knowledge of the conversation** that led to this request - that isolation is deliberate. Work only from the inputs you are given, and from the prompt below.
Any `{{VARIABLE}}` below is filled from
Alternatives in Testing & QA
- Gitnexus Test CI Verifier — GitNexus test and CI reviewer 45.8k ★
- Claude Code Flow — by ruvnet - This mode serves as a code-first orchestration layer, enabling Claude to write, edit, test, and op 22.2k ★
- Review Test Structure — Reviews test code for isolation, independence, readability, documentation quality, and proper setup/teardown 432 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
E2e Test Verifier
E2E spec verifier — runs newly-authored specs via the project's detected E2E command, distrusts false-green pa
Red Quality Gate
Automated quality gate that runs after a failing test is written (RED) and before any implementation (GREEN).
Forge Verify
Forge's Verification agent — actually drives the running app/build to confirm a change works, rather than trus
Engine QA Review Usability
After a change you've asked for is built, checks whether it actually works well for the people who use it — is
Eval Auditor
Audits an evaluation setup (benchmark, A/B test, or model comparison) for methodology errors that would invali
Vine Coder
Autonomously implement a ticketed VINE work slice end-to-end — orient from the ticket and SPEC, implement with
Related Skills
Fire Autonomous
Full autopilot — plan, execute, verify all phases autonomously after PRD is complete
Iterate Centroids Score
Run the long-horizon centroid-score kernel iterate loop autonomously — design 4 variants, JIT-compile, benchma
Copy Check
Build-end pass over the diff's user-facing strings. Applies the project's copy rules and before→after exemplar