Quality

Codex E2E Greet is a test greeter fixture for Codex skills end-to-end tests. It includes the unique suffix a3f9c2 in its skill name so a string match in the agent's output proves Codex loaded this skill.

Codex E2E XYZ Count B8d4e7 is a fixture skill used in end-to-end tests to verify that Codex enumerates skills. It includes a unique suffix so a string match confirms the skill was loaded.

Cross-Review verifies an implementer's diff using an independent sub-agent from a different vendor, reviewing only the diff and contract. It turns blocking issues into fix-tasks and loops until gates are green and no blockers remain.

Pi Native E2E Dev spins up a live local Omnigent server and runner to exercise the native Pi TUI harness end-to-end. Use it when developing, testing, or debugging the pi-native harness, its bridge, extension, auth, or model behavior.

Polly E2E Testing runs deterministic mock-LLM and live CLI checks against the polly multi-agent coding orchestrator's critical user journeys. Use it when developing, debugging, or testing examples/polly, its sub-agents, skills, or guardrails.

Run Load Test drives Omnigent's load-test stack to benchmark concurrency with real host-bound sessions and a mocked LLM. Use it when load-testing, stress-testing, or benchmarking Omnigent under concurrency.

Security Audit examines a codebase or directory for security issues such as hardcoded secrets, injection, unsafe deserialization, weak cryptography, and authorization gaps, then produces a structured findings report. Use it when asked for a security review or vulnerability audit; it reports findings only and never fixes code.

Add Tests generates unit and E2E tests for a completed phase based on UAT criteria and implementation. Use it to classify implementation files, approve a test plan, and commit tests following RED-GREEN conventions.

GSD Audit Fix runs an audit, classifies findings as auto-fixable or manual-only, then fixes auto-fixable issues with test verification and atomic commits. Use it when you want to automate code audit remediation in Claude Code.

GSD Audit Milestone audits milestone completion against original intent before archiving. It checks requirements coverage, cross-phase integration, and end-to-end flows by reading existing verification files and spawning an integration checker.

GSD Audit UAT scans all planning phases for pending, skipped, blocked, and human_needed UAT and verification items, cross-references the codebase to detect stale documentation, and produces a prioritized human test plan. Use it before release or when UAT status is unclear to ensure all verification work is accounted for.

GSD Code Review analyzes source files changed during a phase for bugs, security vulnerabilities, and code quality problems. It spawns a code reviewer agent to produce a severity-classified REVIEW.md artifact.