A quality-first harness for autonomous coding agents that checks work with an independent, default-fail reviewer before accepting it as done. Adds skills for running a task queue, quick lint, type and test checks, and project setup.
@23ag1Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and…
@23ag1Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated…
@23ag1Run completely AUTONOMOUSLY — loop the FULL task engine over the Beads queue, a fresh `claude -p` per task, until the queue is…
@23ag1Use when the user asks to make something faster, try many variants, run recursive optimization, benchmark…
@23ag1Run all configured quality checks (lint, types, tests) in one pass with terse output — reports "clean" when green, and only the…
@23ag1Overview and entry point for the completely harness — a quality-first agent workflow unifying GSD (planning depth), Ralph…
@23ag1Run completely UNDER CONTROL — execute the SINGLE next Beads task through the FULL task engine (understand → map → plan-check →…
@23ag1Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test…
@23ag1Scaffold the completely thin layer into the current repository — Definition of Done, the harness rules snippet in CLAUDE.md, and…
@23ag1Plan a phase or feature DIRECTLY into Beads — no PLAN.md, no markdown bridge. Runs GSD-style socratic discovery + decomposition +…
@23ag1Read a plan document, decompose it into steps, design a per-step agent chain from the ECC catalogue, and emit ready-to-paste…
@23ag1Codified expertise for quality control, non-conformance investigation, root cause analysis, corrective action, and supplier…
@23ag1Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new…
@23ag1Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors…
@23ag1Designs feature architectures by analyzing existing codebase patterns and conventions, then providing implementation blueprints…
@23ag1Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing…
@23ag1Independent, read-only acceptance grader. Invoked at the end of a task to verify it is REALLY done. Default-FAIL — every…
@23ag1GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable…
@23ag1GAN Harness — Planner agent. Expands a one-line prompt into a full product specification with features, sprints, evaluation…
@23ag1Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation,…
@23ag1Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input,…
@23ag1Is this you? Claim your profilePut a plugin at the top of Plugins, from $9
