Daedalai Test Gatekeeper — Testing & QA agent for Claude Code
Dispatch before transitioning a DaedalAI work item from TESTING to DONE to verify that all linked test runs pass.
How to install Daedalai Test Gatekeeper
Installs to ~/.claude/agents/clavaud-daedalai-lifecycle-daedalai-test-gatekeeper.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/clavaud/daedalai-lifecycle/HEAD/agents/daedalai-test-gatekeeper.md -o ~/.claude/agents/clavaud-daedalai-lifecycle-daedalai-test-gatekeeper.md Restart Claude Code, or start a new session, for it to be picked up.
What Daedalai Test Gatekeeper does
name: daedalai-test-gatekeeper description: "Dispatch before transitioning a DaedalAI work item from TESTING to DONE to verify that all linked test runs pass. Blocks the transition if any linked test case is failing, skipped without justification, or stale (no run in the last N days). Read-only to the codebase — does not write code, does not run builds. Use when the orchestrator reaches the QG GATE step on a code project." model: sonnet tools: mcp__plugin_daedalai-lifecycle_daedalai-prod__da
Alternatives in Testing & QA
- Zephyr Scanner — Finds Zephyr Scale test cases linked or relevant to Jira stories, ACs, modules, and release risks 548 ★
- Grid Tester — Use this agent for test strategy, TDD workflows, integration/e2e coverage, and flaky test hardening 523 ★
- Omd Codex Image — Channel-aware image materializer 465 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Daedalai Spec Writer
Dispatch when a DaedalAI work item is in TODO or SPECS status, has hasSpec=false, and needs a structured SPEC
Spec Gatekeeper
Spec Kit final gate before a PR. Read-only check that every requirement and acceptance scenario in spec.md has
Item Executor
Sprint item executor — TDD implementation agent. Receives a spec, runs in an isolated git worktree, writes tes
Mx Quality Keeper
Use this agent when you need a dedicated quality gatekeeper that verifies completed work without writing produ
Verify Execution
STAGE 2 - Runs tests and code to verify AI claims. BLOCKS on test failures, false claims, or runtime errors.
Testing QA
🧪 Use this agent for test design and execution, bug hunting and reproduction, edge-case and coverage analysis
Related Skills
Daedalai Finalize
Finalize a DaedalAI work item — register commits, verify entity links, run lesson check + QG, populate solutio
Archive Task
Move settled fix rows (DONE / SKIPPED) out of backlog.md into backlog-archive.md to keep the backlog lean.
Complete Task
Explicitly transition one identified work item to its tracker's completed state — a handler-dispatched, manual