Plugin Claude Code
Quality-first agent harness: deterministic quality/security gates, evidence-based acceptance (default-FAIL evaluator), and a no-silent-stub contract for Claude Code.
Plugin Claude Code
Quality-first harness for autonomous AI coding agents: deterministic gates + a default-FAIL evaluator in the close path of the loop, over a Beads task spine. Done is earned, not asserted. Unifies GSD + Beads; stack-agnostic.
Agent
Independent, read-only acceptance grader. Invoked at the end of a task to verify it is REALLY done. Default-FAIL — every criterion starts false and only flips to PASS with direct evidence. Catches silent downscoping, disabled tests, and over-graded work. Cannot write code.
Hook
Runs once when the project is set up, executing bootstrap.sh via bash. From 23ag1/completely.
Hook
Runs after a tool call finishes for Edit, Write and MultiEdit tool calls, executing quality-gate.sh and cost-tracker.sh via bash (2 commands). From 23ag1/completely.
Hook
Runs before the agent uses a tool for Bash, Write, Edit, MultiEdit and NotebookEdit tool calls, executing guard-dangerous.sh, guard-close.sh and guard-write-zone.sh via bash (3 commands). From 23ag1/completely.
Skill Claude CodeCodex
Run completely AUTONOMOUSLY — loop the FULL task engine over the Beads queue, a fresh claude -p per task, until the queue is empty. Same complete recipe as /completely:control. Backed by cmpl auto. Run it in the FOREGROUND (blocking) — nested workers only run while the launching session is active; it is…
Skill Claude CodeCodex
Run all configured quality checks (lint, types, tests) in one pass with terse output — reports "clean" when green, and only the failing check's output when not. Token-frugal; configured via completely.toml [check] or auto-detected per stack (front+back). Use before committing or to verify a change. Backed by cmpl…
Skill Claude CodeCodex
Overview and entry point for the completely harness — a quality-first agent workflow unifying GSD (planning depth), Ralph (autonomous loop), and Beads (the spine), under deterministic gate hooks and a default-FAIL evaluator. Use to see what's installed, the command surface, and how to start.
Skill Claude CodeCodex
Run completely UNDER CONTROL — execute the SINGLE next Beads task through the FULL task engine (understand → map → plan-check → parallel subagents → TDD → checks → reviewers → verifier → evaluator → debug-on-fail → commit → close), in this session, showing every step and pausing at human gates. One task done…
Skill Claude CodeCodex
Scaffold the completely thin layer into the current repository — Definition of Done, the harness rules snippet in CLAUDE.md, and an optional project-specific quality command. Use when setting up claude-harness in a new project, or when the user says "harness init", "set up the harness", or "wire up the quality gates…
Skill Claude CodeCodex
Plan a phase or feature DIRECTLY into Beads — no PLAN.md, no markdown bridge. Runs GSD-style socratic discovery + decomposition + a goal-backward self-check, then emits a structured plan that cmpl plan-apply materializes as a Beads epic + worker-contract tasks + dependency waves + human checkpoints. One source of…
Skill Claude CodeCodex
Drive the Beads queue (bd ready) with one engine in two autonomy modes — supervised (GSD wave subagents, human gates at phase boundaries) or unattended (Ralph-style fresh-context loop, stops when the queue is empty). Quality gates + the default-FAIL evaluator run underneath both. Use to execute planned work. Backed by…
Skill Claude CodeCodex
MIGRATION (one-time). Import existing markdown task state (Ralph IMPLEMENTATIONPLAN.md, checkbox task lists) into Beads, idempotently. Use when adopting completely in a repo that has markdown plans, or after an upstream update, to keep Beads the single source of truth. Backed by cmpl sync.
Agent
Software architecture specialist for system design, scalability, and technical decision-making. Use PROACTIVELY when planning new features, refactoring large systems, or making architectural decisions.
Agent
Build and TypeScript error resolution specialist. Use PROACTIVELY when build fails or type errors occur. Fixes build/type errors only with minimal diffs, no architectural edits. Focuses on getting the build green quickly.
Agent
Designs feature architectures by analyzing existing codebase patterns and conventions, then providing implementation blueprints with concrete files, interfaces, data flow, and build order.
Agent
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.
Agent
GAN Harness — Evaluator agent. Tests the live running application via Playwright, scores against rubric, and provides actionable feedback to the Generator.
Agent
GAN Harness — Planner agent. Expands a one-line prompt into a full product specification with features, sprints, evaluation criteria, and design direction.
Agent
Expert planning specialist for complex features and refactoring. Use PROACTIVELY when users request feature implementation, architectural changes, or complex refactoring. Automatically activated for planning tasks.
Agent
Security vulnerability detection and remediation specialist. Use PROACTIVELY after writing code that handles user input, authentication, API endpoints, or sensitive data. Flags secrets, SSRF, injection, unsafe crypto, and OWASP Top 10 vulnerabilities.
Skill Claude CodeCodex
Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics.
Skill Claude CodeCodex
Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.