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.
Borrowing it
Nothing to install: this file belongs to modu-ai/moai-adk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/modu-ai/moai-adk/main/.claude/skills/hns-moaiadk-dev-reference/SKILL.mdgit 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/hns-moaiadk-dev-reference)<a href="https://agentmods.dev/skills/modu-ai/moai-adk/hns-moaiadk-dev-reference"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-adk/hns-moaiadk-dev-reference/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/hns-moaiadk-dev-reference"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-adk/hns-moaiadk-dev-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Rogue Agent · line 164 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Agent Snooping · line 151 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00054 | $0.01051 |
| Opus 5 | $0.00027 | $0.00526 |
| Sonnet 5 | $0.00011 | $0.00210 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
hns-moaiadk-dev-reference 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 10d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hns-moaiadk-dev-reference
moai-adk-go 로컬 dev 레퍼런스 —
CLAUDE.local.md§5/§7/§10 의 작업 특화 상세를 이곳으로 이관 (lazy-load). 세션마다 필요 없는 참고 자료. 항상-로드 컨텍스트 절감용. 소유:hns-*네임스페이스 (user-owned,moai update보존 — CLAUDE.local.md §24). 템플릿 미러 금지.
Version Management (from CLAUDE.local.md §5)
Single Source of Truth
- [HARD]
go.modmodule version + git tags are the authoritative sources - [HARD]
pkg/version/version.goreads from git tags at build time
Version Reference:
- Authoritative Source: Git tags (e.g.,
v1.0.0) - Runtime Access:
pkg/version/version.goviagit describe - Config Display:
.moai/config/sections/system.yaml(updated by release process)
Build Version Injection
Version is injected at build time using ldflags:
# Build with version injection
go build -ldflags="-X github.com/modu-ai/moai-adk/pkg/version.Version=v1.0.0"
# Makefile handles this automatically
make build VERSION=1.0.0
Files Requiring Version Sync
When releasing new version, update:
Documentation Files:
- README.md (Version line)
- README.ko.md (Version line)
- CHANGELOG.md (New version entry)
Configuration Files:
- .moai/config/sections/system.yaml (moai.version)
- internal/template/templates/.moai/config/sections/system.yaml.tmpl (moai.version)
Release Process
- Update CHANGELOG.md with new version entry
- Create git tag:
git tag v1.0.0 - Push tag:
git push origin v1.0.0 - Build release binaries:
make release VERSION=1.0.0
Hook Development (from CLAUDE.local.md §7)
[HARD] Shell Script Hooks Only
moai-adk-go uses shell scripts for hooks, NOT Python:
Hook Wrapper Pattern:
#!/bin/bash
# .claude/hooks/moai/handle-session-start.sh
# Read stdin JSON from Claude Code
INPUT=$(cat)
# Call moai binary with hook subcommand
moai hook session-start <<< "$INPUT"
Why Shell Scripts:
- Faster execution (no Python startup overhead)
- Always available (no dependency on uv/python)
- Cross-platform (bash, /bin/sh)
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.
- 10d ago First seen · 166 lines · 54 tokens per session scan A fa9d6f8a669b
hns-moaiadk-dev-reference is a skill published in the GitHub repository modu-ai/moai-adk (1,204 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 1,051 once invoked, about $0.0003 per session on Opus 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
vigilante-issue-implementation-on-go
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Go repository with idiomatic tooling and security guidance.
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
go-specifications
Structural verification for Go — go vet, -race flag, staticcheck. Load when planning, implementing, or reviewing Go code (.go; go.mod).
concept-teaching
A guided teaching workflow for learning one programming concept at a time in Python, Go, or the code you are working on. TDD means test-driven development, but this description does not say that the add-on teaches TDD.
learning-plan
A Chinese-language planning tool for creating or adjusting short, practical learning routes for Python, Go, mixed-language, or goal-focused programming study.
exercise-coach
A coaching guide for people completing Python, Go, or code-reading exercises. It gives the smallest useful hint first and increases help only when needed.