MoAI-ADK is a Go-based harness that organizes and verifies Claude Code work across planning, implementation, synchronization, and review stages. Developers use it to structure agentic coding tasks, apply quality gates, and route work across language models, while the catalogue entries extend its workflow with skills, hooks, commands, MCP servers, instructions, and settings.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add modu-ai/moai-adk --skill moai-workflow-loopgit clone --depth 1 https://github.com/modu-ai/moai-adkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/modu-ai/moai-adk/moai-workflow-loop)<a href="https://agentmods.dev/skills/modu-ai/moai-adk/moai-workflow-loop"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-adk/moai-workflow-loop/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/modu-ai/moai-adk/moai-workflow-loop"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-adk/moai-workflow-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 75 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Anti-Refusal · line 111 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Prompt Injection · line 202 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.02701 |
| Opus 5.5 | $0.00018 | $0.01080 |
| Sonnet 5.5 | $0.00009 | $0.00540 |
| Haiku 4.5 | $0.00004 | $0.00270 |
Grade A, and why
moai-workflow-loop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ralph Engine
Automated feedback loop system integrating LSP diagnostics, AST-grep security scanning, and test validation for continuous code quality improvement.
Preset Architecture — the Ralph Engine as a goal preset
The /moai loop skill (~/.claude/skills/moai/workflows/loop.md) re-expresses this Ralph engine as a goal preset built ON the goal engine: a scan stage builds a finite issue queue, and the iterate-until-done decision is delegated to the goal engine (stop-goal) with the pre-filled condition "queue drained + diagnostics clean". In this preset architecture, this SKILL.md documents the underlying LSP / AST-grep / test / coverage diagnostic machinery that the goal-preset sweep drives; the preset layers the goal-engine composition on top of that machinery WITHOUT changing it. The four loop quadrants (goal-based sweep, turn-based /moai fix, time-based cadence, proactive CI-watch) are presets on the one goal engine, not independent engines.
Quick Reference
Core Capabilities:
- LSP Integration: Real-time diagnostics from language servers
- AST-grep Scanning: Structural code analysis and security checks
- Feedback Loop: Iterative error correction until completion conditions met
- Hook System: PostToolUse and Stop hooks for seamless Claude Code integration
Key Components:
- .claude/hooks/moai/handle-post-tool.sh (PostToolUse): LSP diagnostics after Write/Edit operations
- .claude/hooks/moai/handle-stop.sh (Stop): Loop iteration control
- ralph.yaml: Configuration settings
Commands:
- /moai: One-click Plan-Run-Sync automation (default)
- /moai loop: Start feedback loop
- /moai fix: One-time auto-fix
When to Use:
- Implementing features with zero-error goal
- Automated code quality improvement
- Continuous integration workflows
- Error-driven development patterns
Implementation Guide
Architecture Overview
The Ralph Engine follows a layered architecture. User commands such as /moai:loop, /moai:fix, and /moai enter the Command Layer. The Command Layer invokes the Hook System, which contains the PostToolUse Hook for LSP diagnostics and the Stop Hook for loop control. The Hook System connects to Backend Services including the LSP Client (MoAILSPClient), AST-grep Scanner, and Test Runner. Backend Services feed into Completion Check which evaluates whether errors are zero, tests pass, and coverage is met. Based on the Completion Check result, the system either continues the loop or completes.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago Changed f7eff606db0f
- 15d ago Changed · -1 lines 3ac749448490
- 1mo ago First seen · 240 lines · 44 tokens per session scan A c313738f274f
moai-workflow-loop is a skill published in the GitHub repository modu-ai/moai-adk (1,236 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 2,701 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
quality-hooks
Language-specific auto-lint/format/typecheck pipeline. Supports Python (ruff+pyright), TypeScript (prettier+eslint+tsc), Go (gofmt+golangci-lint). Auto-fix and convergence loops.
debug
Run /debug to find and fix a bug's root cause: a test failing for an unclear reason, /check verify finding a failure, or behavior being wrong. Runs a reproduce, localize, hypothesize, test, fix, verify loop, makes the minimal fix, and hands a regression test to /test. No features, no extra refactors.
gha
Analyze GitHub Actions failures and identify root causes.
test-generator
Automatically suggest tests for new functions and components. Use when new code is written, functions added, or user mentions testing. Creates test scaffolding with Jest, Vitest, Pytest patterns. Triggers on new functions, components, test requests, testing mentions.
team-fix
Use for the full bug-fix pipeline only on explicit request. Never infer from an ordinary bug fix. Runs the compressed pipeline.